INDEX

Explanations

Lists of winners

np_max-act · gemini-2.0-flash

The neuron detects award‐category headings (phrases like “Best X:” in awards listings).

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

 CharSequence

-0.06

_pop

-0.06

waukee

-0.06

.FirebaseAuth

-0.06

 clearTimeout

-0.06

意

-0.06

AdapterManager

-0.06

OPC

-0.06

احت

-0.06

Mk

-0.06

POSITIVE LOGITS

Canceled

0.07

=>'

0.06

 arithmetic

0.06

ニア

0.06

‌س

0.06

_minutes

0.06

 wrought

0.06

 grátis

0.06

ленные

0.06

 مختصات

0.06

Activations Density 0.010%

Lists of winners

The neuron detects award‐category headings (phrases like “Best X:” in awards listings).

No Comments

No Known Activations

Lists of winners

The neuron detects award‐category headings (phrases like “Best X:” in awards listings).

No Comments

No Known Activations