INDEX

Explanations

these

np_max-act · gemini-2.0-flash

The neuron responds to broad chemical‐industry category terms (like “chemicals” or “medications”).

oai_token-act-pair · o4-mini Triggered by @xinyanhu8

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Monday

-0.07

 někdy

-0.07

AMA

-0.06

 지역

-0.06

 irregular

-0.06

ยะ

-0.06

UserData

-0.06

 потер

-0.06

 Aurora

-0.06

Rating

-0.06

POSITIVE LOGITS

.bukkit

0.06

ें।

0.06

 توان

0.06

 khối

0.06

Incre

0.06

 COPYING

0.06

つの

0.06

-anchor

0.06

--;
↵

0.06

.SelectedIndex

0.06

Activations Density 0.052%

these

The neuron responds to broad chemical‐industry category terms (like “chemicals” or “medications”).

No Comments

No Known Activations