INDEX

Explanations

mathematical symbols and notation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ckett

-0.15

otine

-0.15

ide

-0.14

deaux

-0.14

piar

-0.14

yna

-0.14

{Name

-0.14

ears

-0.14

 Hoch

-0.14

POSITIVE LOGITS

}_

0.19

ANNEL

0.17

rm

0.17

ANEL

0.16

ËĨ

0.14

 gÃ³

0.14

osos

0.14

 station

0.14

 pret

0.14

Activations Density 0.022%

mathematical symbols and notation

No Comments

No Known Activations