INDEX

Explanations

versions of software or programming 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

cin

-0.15

 æ®

-0.15

agan

-0.15

ause

-0.14

ubern

-0.14

jong

-0.14

ersonic

-0.14

/libs

-0.13

redicate

-0.13

mey

-0.13

POSITIVE LOGITS

esch

0.15

itel

0.15

oul

0.15

ìļ±

0.15

edReader

0.14

 usted

0.14

ALAR

0.13

 bÃ¬

0.13

\OptionsResolver

0.13

bes

0.13

Activations Density 0.001%

versions of software or programming components

No Comments

No Known Activations