INDEX

Explanations

various forms of guidance or recommendations aimed at improving processes or situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ematik

-0.14

 sprav

-0.13

sel

-0.13

less

-0.13

erto

-0.13

 Held

-0.13

èĥ

-0.13

anca

-0.13

 ä½ĵ

-0.13

vor

-0.12

POSITIVE LOGITS

 applic

0.15

ForResource

0.15

orial

0.14

 every

0.14

#ad

0.14

 Tricks

0.14

 CONTRIBUTORS

0.14

 everybody

0.14

Ð½Ð°ÑĤ

0.14

 everyone

0.14

Activations Density 0.109%

various forms of guidance or recommendations aimed at improving processes or situations

No Comments

No Known Activations