INDEX

Explanations

geographical or location-based terms

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

iegel

-0.17

arend

-0.16

.WinForms

-0.15

thouse

-0.15

Ã¡zd

-0.15

ottes

-0.15

beits

-0.14

åĬŁ

-0.14

POSITIVE LOGITS

elijke

0.17

most

0.17

ornings

0.16

mine

0.16

ìª½

0.16

 Dakota

0.15

 mine

0.15

-s

0.15

æĸ¹åĲĳ

0.15

Activations Density 0.020%

geographical or location-based terms

No Comments

No Known Activations