INDEX

Explanations

references to organizations and societies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

 Matth

-0.15

*Math

-0.15

Å¡tÃŃ

-0.15

nick

-0.15

 gratuito

-0.14

uego

-0.14

uito

-0.13

Ð»Ð¸ÑĪÐºÐ¾Ð¼

-0.13

kaar

-0.13

Ð½Ð¸ÑĤ

-0.13

POSITIVE LOGITS

ixon

0.14

 membership

0.13

imes

0.13

vim

0.13

spin

0.13

ill

0.13

 Ø®Ø¯

0.13

bum

0.13

-members

0.13

0.12

Activations Density 0.072%

references to organizations and societies

No Comments

No Known Activations