INDEX

Explanations

specific programming or technical terms related to file management and data processing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

itten

-0.15

/REC

-0.14

uito

-0.13

 subs

-0.13

eparator

-0.12

 Roths

-0.12

Å¡nÃŃ

-0.12

emics

-0.12

é¹¿

-0.12

ovan

-0.12

POSITIVE LOGITS

ast

0.66

AST

0.56

ast

0.55

(ast

0.53

est

0.53

ost

0.52

ust

0.50

.ast

0.50

 Bast

0.50

_ast

0.49

Activations Density 0.245%

specific programming or technical terms related to file management and data processing

No Comments

No Known Activations