INDEX

Explanations

references to shade or shaded areas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

orate

-0.16

Ã¤che

-0.16

Ú©Ùĩ

-0.15

iger

-0.15

ptype

-0.15

Ì£

-0.15

ei

-0.15

ea

-0.14

aces

-0.14

POSITIVE LOGITS

 cover

0.17

 Cover

0.17

side

0.15

-cover

0.15

anka

0.14

OPY

0.14

è°·

0.14

Jun

0.14

itta

0.14

+offset

0.14

Activations Density 0.010%

references to shade or shaded areas

No Comments

No Known Activations