INDEX

Explanations

references to burglary

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

ez

-0.17

hra

-0.17

hung

-0.17

ezi

-0.16

ept

-0.16

halten

-0.16

orer

-0.16

hn

-0.16

tparam

-0.15

eru

-0.15

POSITIVE LOGITS

undy

0.49

lar

0.35

und

0.32

undi

0.29

andy

0.27

esses

0.26

UND

0.24

ogne

0.24

ess

0.23

ular

0.23

Activations Density 0.007%

references to burglary

No Comments

No Known Activations