INDEX

Explanations

specific symbols, abbreviations, or codes related to technical or computer programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

Ð»Ð¸Ð½

-0.18

nicos

-0.17

 Fountain

-0.16

 Buccane

-0.16

uzzi

-0.16

Ð»ÑĸÐ½

-0.16

leta

-0.15

 åī

-0.15

 Hanson

-0.15

 Anita

-0.15

POSITIVE LOGITS

plotlib

0.18

azi

0.16

elm

0.15

engo

0.15

ous

0.15

OUS

0.15

CAST

0.15

worthy

0.15

 propTypes

0.15

ificant

0.14

Activations Density 0.006%

specific symbols, abbreviations, or codes related to technical or computer programming contexts

No Comments

No Known Activations