INDEX

Explanations

parentheses and numerical information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

áºŃu

-0.15

ijd

-0.15

áº±

-0.14

 Salem

-0.14

man

-0.14

 tunnels

-0.14

 Maid

-0.13

cie

-0.13

ash

-0.13

id

-0.13

POSITIVE LOGITS

Î®

0.18

BarItem

0.15

uke

0.15

hetto

0.15

dirty

0.15

à¹ĳ

0.15

áº¿n

0.14

ugin

0.14

Sharper

0.14

arus

0.14

Activations Density 0.159%

parentheses and numerical information

No Comments

No Known Activations