INDEX

Explanations

content related to specific geographical locations or landmarks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

sted

-0.16

pedia

-0.15

vx

-0.15

zÃŃ

-0.14

Ñĳ

-0.14

åı¥è¯Ŀ

-0.14

sta

-0.14

azzi

-0.14

tributes

-0.14

_ioctl

-0.13

POSITIVE LOGITS

ban

0.19

iesen

0.15

ben

0.15

ëĳĺ

0.14

dar

0.14

Å±

0.14

ÂŃn

0.14

(strpos

0.14

 Ã©s

0.14

Activations Density 0.003%

content related to specific geographical locations or landmarks

No Comments

No Known Activations