INDEX

Explanations

elements related to online content and references, particularly URLs and HTML structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

Vac

-0.15

ansi

-0.15

Nam

-0.14

antz

-0.14

wald

-0.14

uling

-0.14

 subsequ

-0.14

 blessing

-0.14

lix

-0.13

orm

-0.13

POSITIVE LOGITS

adj

0.24

 noun

0.23

adj

0.22

 verb

0.22

Verb

0.22

verb

0.20

.adj

0.20

Syn

0.20

vb

0.20

 informal

0.19

Activations Density 0.091%

elements related to online content and references, particularly URLs and HTML structure

No Comments

No Known Activations