INDEX

Explanations

punctuation marks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

meld

-0.16

va

-0.15

pell

-0.14

trap

-0.14

pan

-0.14

thouse

-0.14

ataka

-0.14

 Dover

-0.14

plen

-0.14

POSITIVE LOGITS

ood

0.16

.star

0.15

atten

0.14

nton

0.14

ibbon

0.14

 Loud

0.14

Sel

0.14

ess

0.14

ETS

0.14

ZY

0.14

Activations Density 0.000%

punctuation marks

No Comments

No Known Activations