INDEX

Explanations

references to central or focal points in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 centres

-0.16

omu

-0.16

ouser

-0.15

 Centre

-0.15

lore

-0.15

tog

-0.15

sig

-0.15

displayName

-0.14

 centered

-0.14

 typealias

-0.14

POSITIVE LOGITS

pieces

0.33

fold

0.25

 gravity

0.23

 piece

0.22

-piece

0.22

piece

0.22

prise

0.21

line

0.21

point

0.21

Piece

0.21

Activations Density 0.029%

references to central or focal points in various contexts

No Comments

No Known Activations