INDEX

Explanations

mentions of taking breaks

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

amm

-0.16

engo

-0.15

adt

-0.15

irth

-0.15

è£ı

-0.14

itÃ©s

-0.14

Wik

-0.14

 rÃ³wn

-0.13

 ratt

-0.13

xaa

-0.13

POSITIVE LOGITS

orative

0.16

unnel

0.16

$MESS

0.15

á»ĳ

0.15

 ÏĩÏģÏĮ

0.15

unkt

0.15

osaur

0.14

icle

0.14

 Airways

0.14

Ã©ru

0.14

Activations Density 0.014%

mentions of taking breaks

No Comments

No Known Activations