INDEX

Explanations

references to programming concepts and relationships between classes and functions 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 @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ç¬Ķ

-0.16

ael

-0.15

wu

-0.15

apiro

-0.14

eny

-0.13

åı°

-0.13

ooled

-0.13

lg

-0.13

 penetration

-0.13

POSITIVE LOGITS

 contains

0.21

 contain

0.21

contain

0.18

 containing

0.18

udad

0.16

á»ĵi

0.16

 uses

0.15

 Contains

0.15

 contained

0.15

_AST

0.15

Activations Density 0.168%

references to programming concepts and relationships between classes and functions within code structures

No Comments

No Known Activations