INDEX

Explanations

references to programming structures or syntax in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

utton

-0.16

ajar

-0.15

undles

-0.14

 Annotations

-0.14

atatype

-0.14

agram

-0.13

lish

-0.13

&W

-0.13

POSITIVE LOGITS

.Companion

0.15

.adv

0.15

irate

0.14

DataContext

0.14

dÃ¼l

0.14

 lá»ĳi

0.13

Ã¡Äį

0.13

gree

0.13

.Expressions

0.13

ampp

0.13

Activations Density 0.135%

references to programming structures or syntax in code

No Comments

No Known Activations