INDEX

Explanations

punctuation marks and expressions of emotion or tone

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

ceae

-0.16

mor

-0.16

 cons

-0.15

tra

-0.14

è§

-0.14

 twig

-0.14

oÄį

-0.14

 hung

-0.14

roids

-0.14

&_

-0.14

POSITIVE LOGITS

stan

0.15

Å¾iv

0.14

Yao

0.14

artin

0.14

avis

0.14

enson

0.14

 lÃŃ

0.14

_DM

0.14

semb

0.14

.IGNORE

0.14

Activations Density 0.184%

punctuation marks and expressions of emotion or tone

No Comments

No Known Activations