INDEX

Explanations

phrases indicating changes or developments in a situation

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

 Î£Î±

-0.16

okemon

-0.14

.jet

-0.14

ÐºÑĥÐ»ÑĮ

-0.14

å²

-0.13

ivol

-0.13

edly

-0.13

/lg

-0.13

Ø§Ø¸

-0.13

ingo

-0.13

POSITIVE LOGITS

ļĮ

0.16

gen

0.15

 Organisation

0.15

0.13

iliar

0.13

Ĵ

0.13

rows

0.13

usta

0.13

roe

0.13

rome

0.13

Activations Density 0.068%

phrases indicating changes or developments in a situation

No Comments

No Known Activations