INDEX

Explanations

technical terms and queries related to software installation and configuration

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

ÅĻet

-0.16

#ad

-0.15

VML

-0.15

uzzi

-0.14

ashing

-0.14

ifo

-0.14

athi

-0.14

 cljs

-0.14

 Outlook

-0.13

apgolly

-0.13

POSITIVE LOGITS

lib

0.19

canf

0.16

 open

0.16

py

0.16

Transmission

0.15

?q

0.15

soc

0.15

 SEAL

0.15

lib

0.15

Ã©lÃ©

0.15

Activations Density 0.458%

technical terms and queries related to software installation and configuration

No Comments

No Known Activations