INDEX

Explanations

elements and actions related to software operations and UI components

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ampler

-0.15

@show

-0.15

bcm

-0.14

amarin

-0.14

Localization

-0.13

Ð¿ÑĢÐ¸Ð¼ÐµÑĢ

-0.13

ActionCode

-0.13

 pseud

-0.13

stem

-0.13

POSITIVE LOGITS

 none

0.19

edList

0.15

adius

0.15

riel

0.15

Sau

0.14

 nothing

0.14

 Hart

0.14

ãĥ¼ãĥĲ

0.14

.zero

0.14

peq

0.14

Activations Density 0.029%

elements and actions related to software operations and UI components

No Comments

No Known Activations