INDEX

Explanations

references to font styling and formatting codes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

redients

-0.18

empo

-0.17

uji

-0.16

bote

-0.16

icates

-0.15

velle

-0.15

.currentThread

-0.15

agua

-0.15

ebi

-0.14

istrovstvÃŃ

-0.14

POSITIVE LOGITS

by

0.17

its

0.15

ny

0.15

 tens

0.15

Fon

0.14

ighton

0.14

æ³ī

0.14

 Caval

0.14

Field

0.14

Activations Density 0.003%

references to font styling and formatting codes

No Comments

No Known Activations