INDEX

Explanations

words related to compliance and following rules or standards

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

taire

-0.18

è²´

-0.14

emachine

-0.14

ekl

-0.14

excel

-0.14

_PAD

-0.14

ByExample

-0.14

ruk

-0.14

ectar

-0.14

URRE

-0.14

POSITIVE LOGITS

ãĥ¼ãĥ¬

0.17

 Cassidy

0.15

aster

0.15

 adher

0.15

bourg

0.14

exp

0.14

ãĤıãģĽ

0.14

inton

0.14

 coming

0.14

@dynamic

0.14

Activations Density 0.013%

words related to compliance and following rules or standards

No Comments

No Known Activations