INDEX

Explanations

phrases indicating different perspectives or points of view

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ãĤīãģĽ

-0.16

_VIRTUAL

-0.16

leck

-0.15

lun

-0.15

imits

-0.15

rana

-0.15

.Cast

-0.14

rhs

-0.14

 AppBundle

-0.14

alem

-0.14

POSITIVE LOGITS

 view

0.27

view

0.24

 Ð·ÑĢÐµÐ½Ð¸Ñı

0.21

vue

0.21

 blank

0.20

vie

0.19

Blank

0.19

-view

0.19

 Blank

0.19

iv

0.19

Activations Density 0.007%

phrases indicating different perspectives or points of view

No Comments

No Known Activations