INDEX

Explanations

terms related to the adoption and implementation of technology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

zos

-0.17

hos

-0.17

lob

-0.17

CRT

-0.17

ros

-0.15

 Lambert

-0.14

eric

-0.14

soft

-0.14

 leaking

-0.14

oz

-0.14

POSITIVE LOGITS

UNUSED

0.17

andbox

0.17

aro

0.17

umann

0.16

nodoc

0.14

PEED

0.14

ivar

0.14

-prof

0.14

Ã¤nder

0.14

SEO

0.14

Activations Density 0.054%

terms related to the adoption and implementation of technology

No Comments

No Known Activations