INDEX

Explanations

phrases or concepts related to proposals and solutions in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ameron

-0.17

ajs

-0.17

ulumi

-0.16

xfb

-0.15

COLUMN

-0.15

ippy

-0.15

ubbo

-0.15

imest

-0.14

avier

-0.14

ForResource

-0.14

POSITIVE LOGITS

 sine

0.15

ØŃØ¯Ø§Ø«

0.14

_MISC

0.14

Ģìŀ¥

0.14

íĥĿ

0.14

è¤

0.13

éĻĦ

0.13

äº®

0.13

end

0.13

.cn

0.13

Activations Density 0.068%

phrases or concepts related to proposals and solutions in various contexts

No Comments

No Known Activations