INDEX

Explanations

programming-related terms and code structures in a technical discussion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ittal

-0.18

ichier

-0.15

idor

-0.15

ableView

-0.15

 Cheer

-0.15

ombre

-0.15

ieur

-0.14

 cheer

-0.14

posable

-0.14

 McDonald

-0.14

POSITIVE LOGITS

åĢ

0.16

heim

0.15

essler

0.15

chedulers

0.15

usses

0.14

vil

0.14

 exile

0.14

íĦ´

0.14

ker

0.14

afen

0.14

Activations Density 0.387%

programming-related terms and code structures in a technical discussion

No Comments

No Known Activations