INDEX

Explanations

the presence of possessive and related terms that indicate ownership or control

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

ëĭ

-0.15

ÑĢÐ°ÑĤÐ½Ð¾

-0.15

ojis

-0.14

isi

-0.14

ARGIN

-0.14

acman

-0.14

ëıĮ

-0.14

atsapp

-0.14

ensibly

-0.14

ools

-0.14

POSITIVE LOGITS

acher

0.15

sher

0.14

Kit

0.14

orsk

0.14

 directions

0.14

 Brief

0.14

ike

0.14

Brief

0.13

WithOptions

0.13

ãĤ¤ãĤº

0.13

Activations Density 0.003%

the presence of possessive and related terms that indicate ownership or control

No Comments

No Known Activations