INDEX

Explanations

out

np_max-act · gemini-2.0-flash

The neuron fires on tokens that cue arithmetic operations or computation prompts (e.g. “Work,” “Calculate,” “Add,” “Sum,” “Multiply,” “Subtract,” “Put together,” “What is,” 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

Imports

-0.07

#================================================================

-0.07

 Champ

-0.06

محمد

-0.06

<char

-0.06

ูกค

-0.06

(df

-0.06

MVP

-0.06

莫

-0.06

冷

-0.06

POSITIVE LOGITS

-tab

0.08

بات

0.06

 دانشگاه

0.06

subscribe

0.06

gear

0.06

 tonnes

0.06

guide

0.06

hexdigest

0.06

/w

0.06

tab

0.06

Activations Density 0.002%

out

The neuron fires on tokens that cue arithmetic operations or computation prompts (e.g. “Work,” “Calculate,” “Add,” “Sum,” “Multiply,” “Subtract,” “Put together,” “What is,” etc.).

No Comments

No Known Activations

out

The neuron fires on tokens that cue arithmetic operations or computation prompts (e.g. “Work,” “Calculate,” “Add,” “Sum,” “Multiply,” “Subtract,” “Put together,” “What is,” etc.).

No Comments

No Known Activations