INDEX

Explanations

dates and times

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

ibold

-0.14

 Reco

-0.14

ibly

-0.13

Vas

-0.13

Ã¼l

-0.13

ertz

-0.13

ivent

-0.13

qing

-0.13

FFECT

-0.13

irth

-0.13

POSITIVE LOGITS

ople

0.16

asher

0.15

SEQ

0.15

GRP

0.15

akit

0.15

conc

0.14

é¡ĶãĤĴ

0.14

blas

0.14

ood

0.14

ofi

0.14

Activations Density 0.009%

dates and times

No Comments

No Known Activations