INDEX

Explanations

line

np_max-act · gemini-2.0-flash

This neuron selectively activates on technical, domain-specific terms (especially hyphenated or compound keywords) common in engineering and networking contexts.

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

 antib

-0.07

 loyalty

-0.06

にと

-0.06

 있던

-0.06

 orderby

-0.06

 своих

-0.06

 миним

-0.06

 sous

-0.06

 extracted

-0.06

_mix

-0.06

POSITIVE LOGITS

 Humph

0.07

Gets

0.07

raz

0.06

 Üst

0.06

ini

0.06

_facebook

0.06

TCL

0.06

SN

0.06

Bon

0.06

Medical

0.06

Activations Density 0.058%

line

This neuron selectively activates on technical, domain-specific terms (especially hyphenated or compound keywords) common in engineering and networking contexts.

No Comments

No Known Activations

line

This neuron selectively activates on technical, domain-specific terms (especially hyphenated or compound keywords) common in engineering and networking contexts.

No Comments

No Known Activations