INDEX

Explanations

references to different degrees of murder charges

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

¶Į

-0.16

achts

-0.16

jang

-0.15

eyse

-0.15

imbus

-0.15

ErrMsg

-0.15

áº¯t

-0.15

Cel

-0.14

åŀĤ

-0.14

ç¬

-0.14

POSITIVE LOGITS

ãĤ¤ãĥ¤

0.15

 Class

0.15

 Interactive

0.14

chen

0.14

pour

0.14

è¶£

0.14

iac

0.14

chem

0.14

Activations Density 0.003%

references to different degrees of murder charges

No Comments

No Known Activations