INDEX

Explanations

information related to technology products and specifications

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

ERSION

-0.18

eyin

-0.17

Sharper

-0.16

Uvs

-0.16

Ð°ÑĢÑı

-0.15

Ã¼rk

-0.15

Glyph

-0.15

vents

-0.15

åŃ¤

-0.15

xac

-0.15

POSITIVE LOGITS

izzo

0.15

Yes

0.15

NA

0.15

yes

0.15

 expend

0.15

 Jackson

0.15

 practical

0.15

 survival

0.14

 editor

0.14

NA

0.14

Activations Density 0.003%

information related to technology products and specifications

No Comments

No Known Activations