INDEX

Explanations

references to Wisconsin and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ocha

-0.17

ables

-0.17

unter

-0.16

ingly

-0.15

ROID

-0.15

itta

-0.15

 Niet

-0.15

aney

-0.15

aine

-0.14

 Ø¨ÙĨØ¯ÛĮ

-0.14

POSITIVE LOGITS

consin

0.35

dom

0.28

CONS

0.26

DOM

0.23

 cons

0.23

cons

0.22

dom

0.22

-dom

0.20

py

0.20

ÅĤa

0.19

Activations Density 0.009%

references to Wisconsin and related terms

No Comments

No Known Activations