INDEX

Explanations

terms related to gender and its implications in various contexts

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

yan

-0.18

vy

-0.15

oted

-0.15

eltas

-0.15

lashes

-0.14

vip

-0.14

_RING

-0.14

iable

-0.14

ivr

-0.14

ãĥ«ãĥĪ

-0.14

POSITIVE LOGITS

ed

0.35

 roles

0.24

que

0.24

-neutral

0.24

edn

0.23

fluid

0.23

neutral

0.22

 neutral

0.22

less

0.21

-specific

0.20

Activations Density 0.011%

terms related to gender and its implications in various contexts

No Comments

No Known Activations