INDEX

Explanations

references to the game "Worms" and its features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ikan

-0.15

-0.14

imits

-0.14

Ã¡j

-0.14

aj

-0.13

eler

-0.13

agn

-0.13

 churn

-0.13

ewater

-0.13

Ã©

-0.13

POSITIVE LOGITS

rsa

0.15

 tslib

0.15

Charsets

0.15

ushima

0.14

clair

0.14

ASN

0.14

aturas

0.13

Äįan

0.13

vecs

0.13

_WP

0.13

Activations Density 0.023%

references to the game "Worms" and its features

No Comments

No Known Activations