INDEX

Explanations

HTML tags and attributes

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

veys

-0.15

ç¼º

-0.14

ayed

-0.14

rowning

-0.13

 Creek

-0.13

arte

-0.13

xF

-0.13

uter

-0.13

uar

-0.13

POSITIVE LOGITS

AllowAnonymous

0.17

llx

0.17

elas

0.16

ÑĢÑĸÑĪ

0.16

Ð»ÑĸÑĤ

0.15

WindowText

0.15

-NLS

0.14

 erotico

0.14

ixin

0.14

elu

0.14

Activations Density 0.006%

HTML tags and attributes

No Comments

No Known Activations