INDEX

Explanations

class or style attributes used in HTML or CSS

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

deaux

-0.18

inux

-0.16

ategorical

-0.14

doch

-0.14

_FLAG

-0.14

ystick

-0.14

odash

-0.14

.Ui

-0.14

ierge

-0.14

antro

-0.14

POSITIVE LOGITS

Ĥæķ°

0.18

 transit

0.16

 Transit

0.16

ì¹¨

0.15

 anonymous

0.14

bla

0.14

Lon

0.14

antal

0.14

 Ordering

0.13

chi

0.13

Activations Density 0.001%

class or style attributes used in HTML or CSS

No Comments

No Known Activations