INDEX

Explanations

specific letters or symbols within text, possibly in relation to coding or categorization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

icial

-0.15

/GPL

-0.15

-0.14

\widgets

-0.14

 virt

-0.14

 sheer

-0.14

vip

-0.13

Parsed

-0.13

aid

-0.13

 Lindsay

-0.13

POSITIVE LOGITS

å¦Ļ

0.16

 Mane

0.16

ynom

0.15

 Reyn

0.15

nier

0.15

elop

0.15

åŃĹ

0.14

Ð¶Ð°

0.14

aller

0.14

Jag

0.14

Activations Density 0.158%

specific letters or symbols within text, possibly in relation to coding or categorization

No Comments

No Known Activations