INDEX

Explanations

text elements related to web navigation and structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

uzzi

-0.17

.googlecode

-0.15

æ®µ

-0.13

htub

-0.13

 isolate

-0.13

imler

-0.13

ÙıÙĨ

-0.13

-append

-0.13

isol

-0.12

insic

-0.12

POSITIVE LOGITS

 home

0.56

 main

0.48

home

0.45

 Home

0.45

 homepage

0.43

é¦ĸé¡µ

0.42

-home

0.41

 Main

0.41

 MainPage

0.40

Home

0.40

Activations Density 0.134%

text elements related to web navigation and structure

No Comments

No Known Activations