INDEX

Explanations

key concepts related to identity and societal roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

zung

-0.17

/groups

-0.15

riba

-0.15

askell

-0.14

athom

-0.14

awah

-0.14

opsy

-0.14

een

-0.14

baugh

-0.14

isher

-0.14

POSITIVE LOGITS

ìĤ¬íķŃ

0.21

åĻ¨

0.20

ÙĨØ§ÙħÙĩ

0.18

 ÙĨØ§ÙħÙĩ

0.18

 regimen

0.18

 ìĤ¬íķŃ

0.17

 spree

0.17

æĿ¡

0.17

 regime

0.17

åº«

0.17

Activations Density 1.080%

key concepts related to identity and societal roles

No Comments

No Known Activations