INDEX

Explanations

answers or responses that begin with an "A" and are typically followed by a value indicating a degree of completeness or relevance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

 Graham

-0.15

ylie

-0.14

nr

-0.14

ven

-0.14

lect

-0.14

Mev

-0.13

imson

-0.13

ê¶ģ

-0.13

Î¹Î¬

-0.13

POSITIVE LOGITS

templ

0.15

.rad

0.14

arded

0.14

uario

0.14

solete

0.14

umen

0.14

@qq

0.14

 condol

0.14

aminer

0.14

ëĵĿ

0.13

Activations Density 0.003%

answers or responses that begin with an "A" and are typically followed by a value indicating a degree of completeness or relevance

No Comments

No Known Activations