INDEX

Explanations

code constructs and control flow keywords related to conditions and returns

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

abee

-0.16

 '"';↵

-0.14

 ëĭ¤ìļ´ë°Ľê¸°

-0.14

.scalablytyped

-0.14

,exports

-0.14

ãĥĥãĤ·ãĥ¥

-0.14

ives

-0.13

_^(

-0.13

icus

-0.13

FTER

-0.13

POSITIVE LOGITS

 null

0.41

 None

0.38

 NULL

0.36

 empty

0.35

 Null

0.34

 nothing

0.34

 blank

0.33

 none

0.32

 Nothing

0.32

null

0.31

Activations Density 0.463%

code constructs and control flow keywords related to conditions and returns

No Comments

No Known Activations