INDEX

Explanations

references to scientific papers and their publication details

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

apon

-0.16

ars

-0.16

ibi

-0.15

olis

-0.14

tridge

-0.14

ri

-0.14

iÃ¨re

-0.13

pany

-0.13

cci

-0.13

ot

-0.13

POSITIVE LOGITS

COPE

0.15

 Setter

0.15

ATUS

0.15

MPC

0.15

 jenter

0.15

.nextSibling

0.14

 tamb

0.14

UME

0.14

arend

0.14

gnu

0.14

Activations Density 0.007%

references to scientific papers and their publication details

No Comments

No Known Activations