INDEX

Explanations

punctuation/stopwords

np_max-act · gemini-2.0-flash

This neuron fires on procedural or methods-style list markers and measurement expressions—e.g. outline labels (a., b., c.) and quantifiers like “from,” “to,” numeric ranges, and units in scientific protocols.

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

ape

-0.07

Nine

-0.07

 distur

-0.06

 argent

-0.06

(summary

-0.06

bine

-0.06

landa

-0.06

 DOCUMENT

-0.06

 prediction

-0.06

 받아

-0.06

POSITIVE LOGITS

 chronological

0.07

 Meer

0.06

ับความ

0.06

.descripcion

0.06

 aller

0.06

たい

0.06

aggable

0.06

秒

0.06

Rid

0.06

 ความ

0.06

Activations Density 0.637%

punctuation/stopwords

This neuron fires on procedural or methods-style list markers and measurement expressions—e.g. outline labels (a., b., c.) and quantifiers like “from,” “to,” numeric ranges, and units in scientific protocols.

No Comments

No Known Activations