INDEX

Explanations

references to academic or historical chapters and citations

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

auer

-0.19

VERIFY

-0.15

owski

-0.15

ÑĩÐ°ÑĤ

-0.15

 cellFor

-0.15

wart

-0.14

asley

-0.14

ret

-0.14

Å¡ti

-0.14

quet

-0.13

POSITIVE LOGITS

ussion

0.15

OCUS

0.15

unto

0.14

HeaderCode

0.14

ioctl

0.14

ÙĴØ³

0.14

oise

0.14

é¢Ĩ

0.14

Ã®t

0.13

cq

0.13

Activations Density 0.005%

references to academic or historical chapters and citations

No Comments

No Known Activations