INDEX

Explanations

count

np_max-act · gemini-2.0-flash

This neuron detects emphatic, authority-marking keywords (like “statement,” “message,” “business,” “ask,” “good”) that appear at the end of sentences to underscore a point.

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

ale

-0.07

pym

-0.07

ANE

-0.06

 tyto

-0.06

validator

-0.06

Mexico

-0.06

axe

-0.06

 verbal

-0.06

iore

-0.06

 blatantly

-0.06

POSITIVE LOGITS

нос

0.07

 appropriation

0.07

 활동

0.06

ез

0.06

 Marketable

0.06

 doldur

0.06

_DICT

0.06

_FOCUS

0.06

geber

0.06

%c

0.06

Activations Density 0.381%

count

This neuron detects emphatic, authority-marking keywords (like “statement,” “message,” “business,” “ask,” “good”) that appear at the end of sentences to underscore a point.

No Comments

No Known Activations

count

This neuron detects emphatic, authority-marking keywords (like “statement,” “message,” “business,” “ask,” “good”) that appear at the end of sentences to underscore a point.

No Comments

No Known Activations