INDEX

Explanations

cooking instructions and actions in recipes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

çª

-0.15

Ã¶t

-0.14

enders

-0.14

flies

-0.14

åĭĴ

-0.14

ripper

-0.14

izoph

-0.14

alis

-0.14

Ø´Øª

-0.14

Ð»Ð°Ð±

-0.14

POSITIVE LOGITS

 ApiException

0.15

.componentInstance

0.14

asley

0.14

 breakup

0.14

0.13

 Ð¾Ñħ

0.13

ylv

0.13

cop

0.13

inqu

0.13

Activations Density 0.018%

cooking instructions and actions in recipes

No Comments

No Known Activations