INDEX

Explanations

references to "surface" 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 @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

ths

-0.17

sur

-0.16

lon

-0.15

embro

-0.15

frey

-0.15

tl

-0.15

la

-0.15

sak

-0.15

soever

-0.15

lia

-0.15

POSITIVE LOGITS

 tension

0.28

 area

0.27

/interface

0.26

area

0.21

-mounted

0.21

 finish

0.21

-area

0.20

-level

0.20

 Area

0.19

/sub

0.19

Activations Density 0.017%

references to "surface" in various contexts

No Comments

No Known Activations