INDEX

Explanations

references to gender identity, ideology, and political correctness within educational contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

 conservative

-0.16

ingham

-0.15

 conservatives

-0.15

laps

-0.14

OLUMNS

-0.14

 gazet

-0.14

igham

-0.14

olem

-0.14

old

-0.14

Ø§ÙģØ©

-0.13

POSITIVE LOGITS

wyn

0.16

zell

0.15

uru

0.15

bens

0.15

 trendy

0.14

 overrun

0.14

.asp

0.14

.tpl

0.14

umu

0.14

POL

0.14

Activations Density 0.516%

references to gender identity, ideology, and political correctness within educational contexts

No Comments

No Known Activations