INDEX

Explanations

repeated phrases indicating confusion or complexity in music or artistic contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

Ð½Ð°Ð´Ð»ÐµÐ¶

-0.15

YO

-0.15

èŁ

-0.15

ingly

-0.15

elib

-0.14

utto

-0.14

elig

-0.13

peed

-0.13

oldt

-0.13

jour

-0.13

POSITIVE LOGITS

gons

0.16

dere

0.16

rost

0.16

 Loren

0.15

uada

0.15

 ãĤ±

0.15

licit

0.14

egral

0.14

ORE

0.14

ehr

0.14

Activations Density 0.006%

repeated phrases indicating confusion or complexity in music or artistic contexts

No Comments

No Known Activations