INDEX

Explanations

phrases indicating actions or contributions that involve putting or placing something in a specific context

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

itez

-0.18

Ã¡cil

-0.17

rien

-0.17

æµ©

-0.16

ittal

-0.16

apo

-0.15

ulfilled

-0.15

amps

-0.14

ewed

-0.14

itÃ¤

-0.14

POSITIVE LOGITS

nam

0.17

ellas

0.15

cho

0.15

 into

0.14

folio

0.14

 emphasis

0.14

æİª

0.14

itive

0.14

selectAll

0.14

 semiclass

0.14

Activations Density 0.097%

phrases indicating actions or contributions that involve putting or placing something in a specific context

No Comments

No Known Activations