INDEX

Explanations

API

np_max-act · gemini-2.0-flash

The neuron fires on code‐style type declarations and parameter names—especially array syntax like “String[]” and the surrounding identifier tokens.

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

-0.07

set

-0.07

-0.06

 Rotary

-0.06

 Scarlett

-0.06

 wavelength

-0.06

.dropdown

-0.06

POSITIVE LOGITS

.mybatis

0.07

 credentials

0.06

	prop

0.06

 vacc

0.06

 clans

0.06

ěst

0.06

 props

0.06

 Володими

0.06

 персп

0.06

ニニニニ

0.06

Activations Density 0.104%

API

The neuron fires on code‐style type declarations and parameter names—especially array syntax like “String[]” and the surrounding identifier tokens.

No Comments

No Known Activations