INDEX

Explanations

numerical data related to measurements and limits

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

anders

-0.18

Ø¢

-0.15

isy

-0.15

 numbering

-0.14

redicate

-0.14

ÑģÐºÐ»Ð°Ð´

-0.14

á»Ľ

-0.14

izzard

-0.14

elu

-0.13

#+

-0.13

POSITIVE LOGITS

/$

0.17

å·¦åı³

0.16

 minimum

0.15

elts

0.14

_SPECIAL

0.14

ap

0.14

 plus

0.14

 EACH

0.14

ugen

0.14

conds

0.14

Activations Density 0.267%

numerical data related to measurements and limits

No Comments

No Known Activations