INDEX

Explanations

variables and parameters related to data processing functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

otos

-0.17

ÅĻev

-0.15

_PCM

-0.15

ktor

-0.15

ç¥Ń

-0.15

omik

-0.15

 defaultManager

-0.14

 cÃ©lib

-0.14

OTOS

-0.14

ruk

-0.14

POSITIVE LOGITS

0.16

erer

0.15

 opener

0.15

 Lyon

0.15

anno

0.14

thur

0.14

 Cliff

0.14

 Gund

0.14

Activations Density 0.083%

variables and parameters related to data processing functions

No Comments

No Known Activations