INDEX

Explanations

instances of images or pictures in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ssize

-0.17

luv

-0.16

uguay

-0.16

ÐµÐ¶

-0.15

antal

-0.15

-gnu

-0.15

ÙĦÙħØ§ÙĨ

-0.15

Ñİ

-0.14

ãģĴ

-0.14

 Tart

-0.14

POSITIVE LOGITS

å±Ģ

0.15

iae

0.15

0.14

 Rodney

0.14

 ìķ½

0.14

Symfony

0.13

zcze

0.13

 enzym

0.13

ÏĥÏĨ

0.13

hora

0.13

Activations Density 0.001%

instances of images or pictures in the text

No Comments

No Known Activations