INDEX

Explanations

references to knowledge, learning, and understanding in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ulu

-0.15

odd

-0.15

SION

-0.14

dr

-0.14

cape

-0.14

_lineno

-0.14

iline

-0.14

 uncomp

-0.14

ILE

-0.13

liche

-0.13

POSITIVE LOGITS

ä¸įçŁ¥éģĵ

0.37

 ignorance

0.37

 unknown

0.35

 Unknown

0.34

Unknown

0.34

unknown

0.33

.unknown

0.31

 descon

0.31

 UNKNOWN

0.30

_unknown

0.29

Activations Density 0.309%

references to knowledge, learning, and understanding in various contexts

No Comments

No Known Activations