INDEX

Explanations

references to negligence and accountability related to social and political issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

Biz

-0.15

 Branch

-0.15

em

-0.15

hay

-0.14

izm

-0.14

 Hayward

-0.14

iza

-0.14

Biz

-0.14

unde

-0.13

comb

-0.13

POSITIVE LOGITS

AUSE

0.16

å¯¼èĩ´

0.15

 Responsible

0.15

 svÃ½m

0.14

mnop

0.14

Ã¢n

0.14

lero

0.14

mann

0.14

 contrib

0.14

arella

0.14

Activations Density 0.161%

references to negligence and accountability related to social and political issues

No Comments

No Known Activations