INDEX

Explanations

references to local storage and environment variables in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

-0.16

åı£

-0.16

 spotting

-0.15

auga

-0.15

 Spot

-0.15

immel

-0.15

asher

-0.14

 spot

-0.14

wcs

-0.14

POSITIVE LOGITS

OrDefault

0.24

 Ø¨Ø¬

0.15

ourt

0.14

kar

0.14

iais

0.14

yer

0.14

 Cardinal

0.13

XP

0.13

usz

0.13

esa

0.13

Activations Density 0.056%

references to local storage and environment variables in code

No Comments

No Known Activations