INDEX

Explanations

references to royalty and titles of nobility

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

sse

-0.19

apan

-0.17

dition

-0.16

.media

-0.14

immer

-0.14

///<

-0.14

rogram

-0.14

pic

-0.14

ovan

-0.14

POSITIVE LOGITS

rics

0.18

RIP

0.14

Ã¡lo

0.14

 Berk

0.14

vez

0.14

VIC

0.14

 stead

0.13

GenerationStrategy

0.13

ÙĤØ§Øª

0.13

aret

0.13

Activations Density 0.048%

references to royalty and titles of nobility

No Comments

No Known Activations