INDEX

Explanations

numerical data and statistics related to comparisons and measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

Rare

-0.14

itate

-0.14

 Rare

-0.13

ë¡Ŀ

-0.13

$MESS

-0.13

kÃ¼

-0.13

lide

-0.12

omanip

-0.12

_PROXY

-0.12

emer

-0.12

POSITIVE LOGITS

 respectively

0.86

respect

0.83

 respect

0.71

 Respect

0.71

 respectfully

0.65

 ÑģÐ¾Ð¾ÑĤÐ²ÐµÑĤ

0.59

,res

0.57

 respective

0.56

 resp

0.56

 respectful

0.53

Activations Density 0.085%

numerical data and statistics related to comparisons and measurements

No Comments

No Known Activations