INDEX

Explanations

references to sleep and related states or components

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

 suits

-0.14

DESCRIPTION

-0.14

 Ther

-0.14

Baz

-0.13

aison

-0.13

bab

-0.13

 Schwartz

-0.13

tez

-0.13

\modules

-0.13

 æ©Ł

-0.13

POSITIVE LOGITS

onica

0.17

omi

0.15

ibase

0.15

 ÑģÐ¾Ð±Ð¾Ñİ

0.15

 Monte

0.14

ÑĢÑıÐ´Ñĥ

0.14

Æ°á»£ng

0.14

oug

0.14

acob

0.14

ieu

0.14

Activations Density 0.025%

references to sleep and related states or components

No Comments

No Known Activations