INDEX

Explanations

expressions related to individual choices and preferences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

 Clear

-0.15

ÑĢÐµÑī

-0.15

adius

-0.15

 Empty

-0.15

 empty

-0.14

 underlying

-0.14

law

-0.14

uard

-0.14

edad

-0.14

uly

-0.14

POSITIVE LOGITS

 whether

0.15

_UNDEFINED

0.15

 Whether

0.15

ayah

0.14

 decide

0.14

Whether

0.14

Î¼Î¹

0.14

Khu

0.14

à¸·à¸Ńà¸Ĥ

0.14

_HT

0.13

Activations Density 0.194%

expressions related to individual choices and preferences

No Comments

No Known Activations