INDEX

Explanations

mentions of video game titles and related gaming terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

\Domain

-0.15

odont

-0.14

 incident

-0.14

_DROP

-0.14

rosso

-0.14

avan

-0.14

 slime

-0.13

Ð»Ð°Ð½

-0.13

CMP

-0.13

agnost

-0.13

POSITIVE LOGITS

 Assassin

0.26

 Templ

0.21

 Assass

0.21

 Ubisoft

0.21

 assass

0.20

templ

0.19

 templ

0.19

 Brotherhood

0.18

Ez

0.18

 pole

0.17

Activations Density 0.008%

mentions of video game titles and related gaming terms

No Comments

No Known Activations