INDEX

Explanations

references to events or activities occurring within a specific context or setting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

sor

-0.14

ari

-0.13

Î¸ÎŃ

-0.13

fro

-0.13

agus

-0.13

 ************************************************************************

-0.12

 dequeueReusableCellWithIdentifier

-0.12

 rallying

-0.12

Ø±Ùĩ

-0.12

 nederland

-0.12

POSITIVE LOGITS

 tráºŃn

0.17

HttpException

0.17

 ìĿ´ë²Ī

0.16

 upcoming

0.16

ãĥ¼ãĤº

0.15

alars

0.14

ynes

0.14

 cuá»Ļc

0.14

ingleton

0.14

dex

0.14

Activations Density 0.336%

references to events or activities occurring within a specific context or setting

No Comments

No Known Activations