INDEX

Explanations

references to individuals involved in political or social discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

sut

-0.15

 Sabb

-0.15

å½©ç¥¨

-0.15

enza

-0.15

 ethnic

-0.14

ennon

-0.14

 Ethnic

-0.14

 Colbert

-0.14

 Klopp

-0.14

xFFFFFFFF

-0.14

POSITIVE LOGITS

Cmd

0.19

 Geoffrey

0.18

ãĤµãĥ¼

0.17

 Trevor

0.17

 Lady

0.16

 Alec

0.16

Vy

0.15

 Brooke

0.15

 Guinness

0.15

Activations Density 0.167%

references to individuals involved in political or social discussions

No Comments

No Known Activations