INDEX

Explanations

inquiries that request additional information or clarification

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

conti

-0.16

iards

-0.16

Â¨

-0.14

 interdisciplinary

-0.14

iado

-0.13

UEL

-0.13

resar

-0.13

cac

-0.13

alog

-0.13

POSITIVE LOGITS

/all

0.16

ÑģÐ¸Ñħ

0.16

quier

0.14

hone

0.14

.heroku

0.14

ais

0.14

indh

0.14

egree

0.14

remaining

0.14

ICENSE

0.14

Activations Density 0.045%

inquiries that request additional information or clarification

No Comments

No Known Activations