INDEX

Explanations

user

np_max-act · gemini-2.0-flash

The neuron activates on occurrences of “user” (or its plural “users”) in technical or patent‐style descriptions.

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Where

-0.06

_bytes

-0.06

ISS

-0.06

 swung

-0.06

 عامل

-0.06

%m

-0.06

Sal

-0.06

 větší

-0.06

 гла

-0.06

 Director

-0.06

POSITIVE LOGITS

评价

0.08

 Mandal

0.07

 Musical

0.06

oppers

0.06

 господар

0.06

 merupakan

0.06

 acompañ

0.06

绩

0.06

chlor

0.06

َ

0.06

Activations Density 0.079%

user

The neuron activates on occurrences of “user” (or its plural “users”) in technical or patent‐style descriptions.

No Comments

No Known Activations