INDEX

Explanations

formatting indicators for emphasis and lists

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

ationship

-0.16

estruction

-0.16

ropped

-0.15

Ìģt

-0.15

axed

-0.15

 Mour

-0.15

vens

-0.14

imes

-0.14

erc

-0.14

elt

-0.14

POSITIVE LOGITS

0.16

esz

0.15

unami

0.14

ussy

0.14

tÃŃ

0.14

iyan

0.14

ãĥ£

0.14

AndView

0.14

Activations Density 0.013%

formatting indicators for emphasis and lists

No Comments

No Known Activations