INDEX

Explanations

programming-related syntax and data manipulation commands

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

urator

-0.15

arial

-0.15

Ð°ÑĢÑĮ

-0.14

 Rising

-0.14

Ø§Ø´Ø©

-0.14

.tight

-0.13

ãĤīãģĦ

-0.13

pek

-0.13

odia

-0.13

ARY

-0.13

POSITIVE LOGITS

 paste

0.30

NA

0.24

 LETTER

0.23

paste

0.23

seq

0.23

NA

0.22

 Paste

0.22

rep

0.22

Paste

0.22

FALSE

0.21

Activations Density 0.023%

programming-related syntax and data manipulation commands

No Comments

No Known Activations