INDEX

Explanations

HTML comments and documentation markers in a text

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

 Weather

-0.15

observ

-0.15

pro

-0.15

 imper

-0.14

onu

-0.14

 observ

-0.14

inker

-0.14

eson

-0.14

 Armour

-0.14

/session

-0.14

POSITIVE LOGITS

opal

0.15

ÛĮØ¯ÙĨ

0.15

STALL

0.15

asant

0.15

ElementsBy

0.14

Streamer

0.14

nant

0.14

.Stream

0.14

ElementsByTagName

0.14

ERAL

0.14

Activations Density 0.004%

HTML comments and documentation markers in a text

No Comments

No Known Activations