INDEX

Explanations

phrases and terms indicating quality or characteristics of people, places, or things

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

deo

-0.17

aign

-0.15

 Waters

-0.15

ProcessEvent

-0.14

lm

-0.14

 hers

-0.14

æ¢Ŀ

-0.14

odia

-0.14

angi

-0.13

lech

-0.13

POSITIVE LOGITS

 bunch

0.16

 buflen

0.14

fleet

0.14

iversit

0.14

agrams

0.14

 subset

0.14

Yaz

0.14

ixe

0.14

zar

0.14

odos

0.14

Activations Density 0.166%

phrases and terms indicating quality or characteristics of people, places, or things

No Comments

No Known Activations