INDEX

Explanations

attributes and values commonly used in markup languages or web development

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

yard

-0.16

uard

-0.15

SWG

-0.15

ez

-0.15

ÑĢÐ°Ñĩ

-0.14

ogn

-0.14

VOID

-0.14

ache

-0.14

ÑĥÑĤÐ¸

-0.13

verse

-0.13

POSITIVE LOGITS

adays

0.20

odore

0.19

0.18

andre

0.16

atre

0.16

enticator

0.16

/=

0.16

èĪ¬

0.15

à¤µà¤¤

0.15

stitutions

0.15

Activations Density 0.121%

attributes and values commonly used in markup languages or web development

No Known Activations