INDEX

Explanations

references to research publications or citations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

urret

-0.16

orman

-0.15

ç¼

-0.15

icaret

-0.14

Ã¢u

-0.14

allis

-0.14

slu

-0.14

vla

-0.14

 Toast

-0.14

mie

-0.14

POSITIVE LOGITS

éĹ¨

0.18

InView

0.17

itus

0.17

éĸĢ

0.16

 AndAlso

0.14

ä»®

0.14

 Fitz

0.14

 Evet

0.14

Rhe

0.14

TER

0.13

Activations Density 0.000%

references to research publications or citations

No Comments

No Known Activations