INDEX

Explanations

comparisons between movies and their performances

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

ascript

-0.15

ospels

-0.15

pollo

-0.15

 äºİ

-0.15

ospel

-0.15

ksen

-0.14

ologne

-0.14

ernel

-0.14

 Bilim

-0.14

vos

-0.14

POSITIVE LOGITS

Lam

0.18

 Lage

0.18

 Cham

0.17

 Maine

0.17

Uri

0.16

eka

0.16

Ka

0.16

 cham

0.15

åłĤ

0.15

 Phill

0.15

Activations Density 0.022%

comparisons between movies and their performances

No Comments

No Known Activations