INDEX

Explanations

mentions of viewing, touring, or showing properties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

uni

-0.16

abez

-0.15

imon

-0.15

-0.14

Verdana

-0.14

omas

-0.14

.nih

-0.14

Fav

-0.14

 grav

-0.14

POSITIVE LOGITS

angen

0.17

ingen

0.16

ãģıãĤī

0.15

 Beste

0.15

orsi

0.14

ÑĨÐ¾

0.14

ÏĩÏģÎ¹

0.14

eken

0.14

edd

0.14

hipster

0.14

Activations Density 0.242%

mentions of viewing, touring, or showing properties

No Comments

No Known Activations