INDEX

Explanations

details related to legal proceedings and charges

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

this

-0.14

that

-0.14

agos

-0.14

 Ð¶Ðµ

-0.13

ie

-0.13

åĺĽ

-0.13

OSC

-0.13

 ourselves

-0.12

Essay

-0.12

adm

-0.12

POSITIVE LOGITS

 according

0.47

 said

0.37

according

0.36

 officials

0.36

 sources

0.29

 authorities

0.29

 spokesman

0.28

 spokeswoman

0.27

said

0.27

 spokesperson

0.24

Activations Density 0.078%

details related to legal proceedings and charges

No Comments

No Known Activations