INDEX

Explanations

phrases indicating commitment and support

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

yn

-0.19

kind

-0.17

IVITY

-0.17

 quite

-0.15

 kind

-0.15

brtc

-0.15

ÑħÐ¾Ð´

-0.14

 Quite

-0.14

inement

-0.14

_kind

-0.14

POSITIVE LOGITS

 sound

0.17

exus

0.17

 friction

0.16

 robust

0.16

rob

0.15

commit

0.15

 suite

0.15

tera

0.15

achts

0.15

0.14

Activations Density 0.228%

phrases indicating commitment and support

No Comments

No Known Activations