INDEX

Explanations

statistical values and significance in experimental data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

raj

-0.19

rega

-0.17

peÄį

-0.15

atsby

-0.14

erto

-0.14

endet

-0.14

unch

-0.14

å»º

-0.14

beros

-0.14

POSITIVE LOGITS

è¾ŀ

0.16

sWith

0.15

adan

0.14

Ã¢ncia

0.14

 Kitt

0.13

JB

0.13

aven

0.13

 Dich

0.13

 volley

0.13

oola

0.13

Activations Density 0.016%

statistical values and significance in experimental data

No Comments

No Known Activations