INDEX

Explanations

document descriptions

np_max-act · gemini-2.0-flash

This neuron primarily detects section or subsection headings (e.g. titles like “Dependencies,” “Our Goal,” “Installing SoftHSM,” etc.).

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

-compatible

-0.07

мещ

-0.07

 gere

-0.07

 converge

-0.06

 pipeline

-0.06

λη

-0.06

 migration

-0.06

,the

-0.06

ène

-0.06

 campaign

-0.06

POSITIVE LOGITS

////////////////////////////////////////////////////////////////////////////////

0.07

@login

0.07

 mysl

0.06

UUID

0.06

-thirds

0.06

 Mathf

0.06

Buttons

0.06

 Counsel

0.06

 Might

0.06

/********************************

0.06

Activations Density 0.097%

document descriptions

This neuron primarily detects section or subsection headings (e.g. titles like “Dependencies,” “Our Goal,” “Installing SoftHSM,” etc.).

No Comments

No Known Activations