INDEX

Explanations

ISBN numbers or cataloging information associated with books

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

-0.14

zano

-0.14

acher

-0.14

vÅ¯

-0.14

 Marxism

-0.14

 Inquiry

-0.14

 Coord

-0.13

ÏĥÏĥÎ±

-0.13

zew

-0.13

 Conn

-0.13

POSITIVE LOGITS

aed

0.16

ĵn

0.15

.cx

0.14

CORE

0.14

 fich

0.14

orney

0.14

toolbox

0.14

eah

0.14

uhl

0.14

ROLS

0.13

Activations Density 0.021%

ISBN numbers or cataloging information associated with books

No Comments

No Known Activations