INDEX

Explanations

criticism

np_max-act · gemini-2.0-flash

The neuron detects mentions of critics and criticism (e.g. critic, review, criticism, critic names).

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

INF

-0.07

fcntl

-0.06

 computed

-0.06

bit

-0.06

líd

-0.06

'['

-0.06

 monstrous

-0.06

non

-0.06

("**

-0.06

POSITIVE LOGITS

Secure

0.07

 libert

0.07

 мест

0.07

 güvenli

0.06

OCI

0.06

 उपलब

0.06

.enabled

0.06

(&_

0.06

_intersect

0.06

 inflammation

0.06

Activations Density 0.054%

criticism

The neuron detects mentions of critics and criticism (e.g. critic, review, criticism, critic names).

No Comments

No Known Activations