INDEX

Explanations

terms associated with technological interfaces and functionality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

Å¡ov

-0.14

iked

-0.14

Ìģc

-0.13

ãĥ»ãĥ»ãĥ»↵↵

-0.13

ites

-0.13

Î½Î¿Ïį

-0.12

ÑĪÐµÐ²

-0.12

"**

-0.12

ere

-0.12

 aldÄ±ÄŁÄ±

-0.12

POSITIVE LOGITS

crest

0.15

elier

0.15

xdb

0.14

ults

0.14

 pute

0.14

Ã©mon

0.14

wil

0.14

Streamer

0.13

ufe

0.13

atron

0.13

Activations Density 0.875%

terms associated with technological interfaces and functionality

No Comments

No Known Activations