INDEX

Explanations

steps

np_max-act · gemini-2.0-flash

The neuron fires on procedural step markers or counts—e.g. “Step,” “steps,” and similar numbered‐step indicators in a method description.

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

 neuken

-0.06

handled

-0.06

 Verm

-0.06

#index

-0.06

 relic

-0.06

nn

-0.06

 thinner

-0.06

 películ

-0.06

 Throughout

-0.06

_memory

-0.05

POSITIVE LOGITS

 приг

0.07

ايد

0.07

デル

0.06

.maxcdn

0.06

 Ле

0.06

 Provincial

0.06

bell

0.06

 paving

0.06

 diye

0.06

oko

0.06

Activations Density 0.009%

steps

The neuron fires on procedural step markers or counts—e.g. “Step,” “steps,” and similar numbered‐step indicators in a method description.

No Comments

No Known Activations