INDEX

Explanations

Code or documentation snippets

np_max-act · gemini-2.0-flash

This neuron detects numbered list markers and numeric enumerations (e.g., “1.”, “2.”, “3.”, and similar decimal or index tokens) in the text.

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

_bh

-0.07

(test

-0.07

REFER

-0.07

_header

-0.07

 ninete

-0.06

ULO

-0.06

 ancor

-0.06

 October

-0.06

Basket

-0.06

_kw

-0.06

POSITIVE LOGITS

À

0.06

 hủy

0.06

 آثار

0.06

.ss

0.06

なる

0.06

ابة

0.06

 tình

0.06

霊

0.06

ения

0.06

秒

0.06

Activations Density 0.093%

Code or documentation snippets

This neuron detects numbered list markers and numeric enumerations (e.g., “1.”, “2.”, “3.”, and similar decimal or index tokens) in the text.

No Comments

No Known Activations