INDEX

Explanations

.substring

np_max-act · gemini-2.0-flash

The neuron fires on Java source‐code scaffolding—especially package/import declarations and related keywords.

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

cheng

-0.07

 turnout

-0.06

Jamie

-0.06

참

-0.06

 forces

-0.06

福

-0.06

lz

-0.06

時代

-0.06

Wel

-0.06

Yang

-0.06

POSITIVE LOGITS

.substr

0.10

.substring

0.08

substr

0.07

boa

0.07

νομ

0.07

charge

0.07

	pthread

0.07

_app

0.07

usta

0.07

AccessException

0.07

Activations Density 0.005%

.substring

The neuron fires on Java source‐code scaffolding—especially package/import declarations and related keywords.

No Comments

No Known Activations

.substring

The neuron fires on Java source‐code scaffolding—especially package/import declarations and related keywords.

No Comments

No Known Activations