INDEX

Explanations

issues related to problems and their discussions

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

ãĥ³ãĥĳ

-0.17

é¤¨

-0.15

ÑĥÑģÑĤÐ¸

-0.14

stanov

-0.14

uren

-0.14

stro

-0.14

agma

-0.14

athers

-0.14

-framework

-0.13

.dy

-0.13

POSITIVE LOGITS

tap

0.14

 rall

0.14

eref

0.14

 this

0.14

çĴĥ

0.14

ÐµÐºÑģ

0.13

this

0.13

enticator

0.13

ying

0.13

_UPPER

0.13

Activations Density 0.053%

issues related to problems and their discussions

No Comments

No Known Activations