INDEX

Explanations

references to the physical characteristics and functionalities of a machine

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

pac

-0.15

oner

-0.15

vig

-0.14

Wrapped

-0.14

Ã©nÃ©

-0.14

.skip

-0.14

 Franken

-0.14

.transfer

-0.14

çŃĭ

-0.13

 Starter

-0.13

POSITIVE LOGITS

 fold

0.32

 folding

0.31

-fold

0.30

fold

0.28

 Folding

0.28

Fold

0.28

 Fold

0.27

 folded

0.27

 folds

0.27

 unfolded

0.27

Activations Density 0.102%

references to the physical characteristics and functionalities of a machine

No Comments

No Known Activations