INDEX

Explanations

phrases and connectors that indicate complexity and nuance in discussions around social and institutional issues

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

leta

-0.14

aan

-0.14

abb

-0.14

eus

-0.13

ine

-0.13

apis

-0.13

 useClass

-0.13

TL

-0.13

rosse

-0.13

POSITIVE LOGITS

etc

0.39

etc

0.32

/etc

0.24

çŃī

0.20

 ÑĤÐ¾ÑīÐ¾

0.17

 finally

0.17

 whatever

0.16

 blah

0.16

 çŃī

0.16

iferay

0.16

Activations Density 0.076%

phrases and connectors that indicate complexity and nuance in discussions around social and institutional issues

No Comments

No Known Activations