INDEX

Explanations

references to visual or descriptive features related to shape or outline

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

Ã¤hr

-0.18

ebi

-0.18

odable

-0.16

eyse

-0.15

sport

-0.15

meteor

-0.15

riott

-0.14

 squat

-0.14

infeld

-0.13

erap

-0.13

POSITIVE LOGITS

0.15

istrovstvÃŃ

0.14

ingham

0.14

ettle

0.14

-assets

0.13

-Ta

0.13

ously

0.13

ÐºÑĢÐµÑĤ

0.13

fig

0.13

Activations Density 0.008%

references to visual or descriptive features related to shape or outline

No Comments

No Known Activations