INDEX

Explanations

mentions of kitchens and kitchen-related features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

-0.16

-0.15

tors

-0.15

-0.14

eed

-0.14

oothing

-0.14

sus

-0.14

POSITIVE LOGITS

etics

0.16

İ

0.15

iser

0.15

ete

0.15

idata

0.15

á»³

0.14

lad

0.14

.mj

0.14

/bar

0.14

erce

0.14

Activations Density 0.019%

mentions of kitchens and kitchen-related features

No Comments

No Known Activations