INDEX

Explanations

elements and attributes within code structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

rana

-0.18

rane

-0.15

 Southern

-0.14

oped

-0.14

.Aggressive

-0.14

MatrixXd

-0.14

lt

-0.13

 Kathryn

-0.13

COPE

-0.13

YRO

-0.13

POSITIVE LOGITS

icer

0.17

Charset

0.15

/from

0.14

ãģ°ãģĭãĤĬ

0.14

Assets

0.13

ilon

0.13

anni

0.13

ValidationError

0.13

arranty

0.13

 annonces

0.13

Activations Density 0.021%

elements and attributes within code structures

No Comments

No Known Activations