INDEX

Explanations

file names, links, and other references to digital content

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

zan

-0.16

bay

-0.15

 kolo

-0.15

Ð´Ñĥ

-0.14

theid

-0.14

zed

-0.14

rew

-0.13

Ä°K

-0.13

PARSE

-0.13

 Profiles

-0.13

POSITIVE LOGITS

eker

0.17

ebi

0.15

å·

0.14

mos

0.14

æħİ

0.13

bose

0.13

ML

0.13

red

0.13

igin

0.13

Activations Density 0.000%

file names, links, and other references to digital content

No Comments

No Known Activations