INDEX

Explanations

titles of films, games, or media

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ÏīÎ¼Î±

-0.19

baugh

-0.17

ä¸²

-0.15

alama

-0.15

mrt

-0.15

 Geek

-0.15

bjerg

-0.15

stad

-0.14

altung

-0.14

èħ

-0.14

POSITIVE LOGITS

.manager

0.16

Ð»Ð¸Ð¶

0.16

VR

0.15

 Surv

0.15

 titles

0.15

 mode

0.15

 Euro

0.15

oley

0.14

isoft

0.14

 Mode

0.14

Activations Density 0.123%

titles of films, games, or media

No Comments

No Known Activations