INDEX

Explanations

phrases that indicate subtle suggestions or implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

arde

-0.17

Ø¨Ø§Ø±

-0.16

bar

-0.15

agal

-0.15

enga

-0.14

/install

-0.14

olly

-0.14

ÙĤÙħ

-0.14

iser

-0.14

lin

-0.14

POSITIVE LOGITS

 hint

0.21

 towards

0.19

 toward

0.19

lessly

0.18

blick

0.18

 hints

0.17

utherland

0.16

ingly

0.16

erglass

0.16

Trou

0.16

Activations Density 0.026%

phrases that indicate subtle suggestions or implications

No Comments

No Known Activations