INDEX

Explanations

phrases that prompt critical thinking or reflection

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

 Hacker

-0.15

.named

-0.14

extr

-0.14

Ì§

-0.14

ighton

-0.14

idal

-0.14

yen

-0.14

ellaneous

-0.13

aphrag

-0.13

ches

-0.13

POSITIVE LOGITS

åĲ§

0.17

McL

0.14

AMESPACE

0.14

(++

0.14

 yourself

0.14

.poly

0.13

 though

0.13

tout

0.13

 Escort

0.13

asan

0.13

Activations Density 0.064%

phrases that prompt critical thinking or reflection

No Comments

No Known Activations