INDEX

Explanations

urrence

np_max-act · gemini-2.0-flash

This neuron activates on the heading-like term “Occurrence,” flagging when the text is reporting the occurrence (prevalence) of something.

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

 diet

-0.07

_border

-0.07

 Dust

-0.07

 Spurs

-0.06

Pad

-0.06

IT

-0.06

 Salt

-0.06

 Peel

-0.06

(id

-0.06

 sanit

-0.06

POSITIVE LOGITS

 occurrence

0.11

OCC

0.08

 occurrences

0.08

 rencont

0.08

发生

0.07

urrence

0.07

 obvyk

0.07

 homeowners

0.07

getNext

0.07

 ever

0.07

Activations Density 0.008%

urrence

This neuron activates on the heading-like term “Occurrence,” flagging when the text is reporting the occurrence (prevalence) of something.

No Comments

No Known Activations

urrence

This neuron activates on the heading-like term “Occurrence,” flagging when the text is reporting the occurrence (prevalence) of something.

No Comments

No Known Activations