INDEX

Explanations

names, particularly those that are feminine or often associated with women

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

juan

-0.18

éħ

-0.15

obus

-0.14

Lifecycle

-0.14

indi

-0.14

erah

-0.14

ÑĮÐ¼Ð¸

-0.14

yb

-0.14

iets

-0.14

Mid

-0.13

POSITIVE LOGITS

ÑĩÐµ

0.16

áº«

0.16

ãĥ³

0.16

amo

0.15

les

0.14

à¥Īà¤¨

0.14

strate

0.14

_multiplier

0.14

awner

0.14

ãĥ³ãĥ

0.14

Activations Density 0.048%

names, particularly those that are feminine or often associated with women

No Comments

No Known Activations