INDEX

Explanations

terms and phrases related to transgender individuals and issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

elez

-0.15

datable

-0.15

ÙĪÙĤØª

-0.15

ahat

-0.15

 Boeh

-0.15

_INET

-0.15

Predicate

-0.14

(predicate

-0.14

dic

-0.13

ÎºÎŃ

-0.13

POSITIVE LOGITS

istrovstvÃŃ

0.15

NAV

0.15

up

0.15

quo

0.14

ize

0.14

ania

0.14

rawn

0.14

oram

0.14

ed

0.14

Activations Density 0.016%

terms and phrases related to transgender individuals and issues

No Comments

No Known Activations