INDEX

Explanations

technical instructions related to software usage and systems integration

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

udeau

-0.18

inger

-0.15

ninger

-0.15

ì±Ħ

-0.14

 Intercept

-0.14

æŃ

-0.14

saida

-0.14

 everything

-0.13

amik

-0.13

 tudo

-0.13

POSITIVE LOGITS

 built

0.19

 either

0.17

æµ

0.17

ãĤ¦ãĤ¹

0.16

 link

0.15

 Morrison

0.15

 command

0.15

ought

0.15

 normal

0.15

ãĥĨãĥ«

0.15

Activations Density 0.101%

technical instructions related to software usage and systems integration

No Comments

No Known Activations