INDEX

Explanations

phrases related to creating and performing tasks or activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

iano

-0.17

igar

-0.16

otal

-0.15

agi

-0.14

inst

-0.14

¯

-0.14

ë°°

-0.14

 neither

-0.14

 Skip

-0.14

POSITIVE LOGITS

 safely

0.16

jin

0.15

 safe

0.14

lobals

0.14

wald

0.14

Ler

0.14

ÙĩØ§Ø±

0.14

abase

0.14

 Mood

0.13

ushima

0.13

Activations Density 0.146%

phrases related to creating and performing tasks or activities

No Comments

No Known Activations