INDEX

Explanations

parentheses and page numbers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

į¼

-0.17

cers

-0.17

ÅĻet

-0.16

itness

-0.16

¨

-0.15

Lexer

-0.15

ucer

-0.14

ë¡Ģ

-0.14

letcher

-0.14

retch

-0.13

POSITIVE LOGITS

¹Ħ

0.16

æ»

0.15

Lau

0.15

undy

0.15

Swe

0.14

bourg

0.14

lay

0.14

unner

0.14

Activations Density 0.101%

parentheses and page numbers

No Comments

No Known Activations