INDEX

Explanations

technical terms and programming-related keywords

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

 Bever

-0.15

 Bernstein

-0.15

aur

-0.14

enko

-0.14

rez

-0.14

mess

-0.14

 mine

-0.14

 Watts

-0.14

mos

-0.13

POSITIVE LOGITS

abbo

0.17

pyx

0.15

nej

0.15

çķĮ

0.15

orage

0.15

bast

0.14

arak

0.14

Î»Î»Î±

0.14

avanaugh

0.14

caff

0.14

Activations Density 0.106%

technical terms and programming-related keywords

No Comments

No Known Activations