INDEX

Explanations

terms related to technology and computing

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

ined

-0.16

Mog

-0.16

 ferr

-0.15

oÅ¾

-0.15

appable

-0.14

ÏĢÎµ

-0.14

aul

-0.14

 btnCancel

-0.14

apan

-0.14

ped

-0.14

POSITIVE LOGITS

0.16

 clearance

0.15

imet

0.15

ga

0.14

Kub

0.14

Î»ÎŃ

0.14

 Placeholder

0.14

adow

0.13

ISK

0.13

IRCLE

0.13

Activations Density 0.018%

terms related to technology and computing

No Comments

No Known Activations