INDEX

Explanations

legal and academic terminology related to charges and reports

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

ce

-0.15

nd

-0.15

arc

-0.14

 respectively

-0.14

tember

-0.14

'er

-0.14

ãĤ¹ãĥŀ

-0.14

ãĥ¼ãĥŃ

-0.14

abase

-0.14

POSITIVE LOGITS

(s

0.19

heim

0.17

chos

0.16

Ìĥ

0.15

_closure

0.15

 heap

0.15

Å¯

0.15

Ð°Ð¼Ð¸

0.15

buzz

0.15

bonus

0.15

Activations Density 0.443%

legal and academic terminology related to charges and reports

No Comments

No Known Activations