INDEX

Explanations

terms and phrases related to programming concepts and technical specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 Ð¿Ð¾Ð±Ð°

-0.16

inea

-0.15

ick

-0.14

rez

-0.14

men

-0.14

 Ð½ÐµÐ³Ð¾

-0.14

avez

-0.14

oni

-0.13

out

-0.13

andra

-0.13

POSITIVE LOGITS

 Dank

0.16

ILLED

0.15

LATED

0.15

 Gratuit

0.14

=Value

0.14

ennent

0.14

 Ð½Ð°

0.14

&type

0.14

FRING

0.14

Activations Density 0.059%

terms and phrases related to programming concepts and technical specifications

No Comments

No Known Activations