INDEX

Explanations

references to characters and organizations within fictional and real-world narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

eyse

-0.15

errmsg

-0.15

Î¯Îº

-0.14

forman

-0.14

Ð»Ð°Ð±

-0.14

atron

-0.13

BackStack

-0.13

Downloading

-0.13

ë§ī

-0.13

/licenses

-0.13

POSITIVE LOGITS

Ìģ

0.21

ay

0.14

ab

0.14

arel

0.14

ix

0.13

.exe

0.13

elier

0.13

ider

0.13

ress

0.13

za

0.13

Activations Density 1.093%

references to characters and organizations within fictional and real-world narratives

No Comments

No Known Activations