INDEX

Explanations

legal context

np_max-act · gemini-2.0-flash

The neuron detects words relating to the revealing or release of information (e.g., “release,” “disclosure”).

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

il

-0.07

Tap

-0.07

-vous

-0.07

.Obj

-0.07

.Geometry

-0.07

ith

-0.07

 Rated

-0.06

/XML

-0.06

 propose

-0.06

 myths

-0.06

POSITIVE LOGITS

.nom

0.07

ott

0.07

ращ

0.06

ému

0.06

.bi

0.06

Vari

0.06

vg

0.06

(This

0.06

(itemView

0.06

ไซ

0.06

Activations Density 0.034%

legal context

The neuron detects words relating to the revealing or release of information (e.g., “release,” “disclosure”).

No Comments

No Known Activations