INDEX

Explanations

after

np_max-act · gemini-2.0-flash

The neuron flags temporal markers of something occurring afterward—words like “after,” “aftermath,” and related tokens indicating “following” events.

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

 Steele

-0.06

�

-0.06

 Eggs

-0.06

唯一

-0.06

iggs

-0.06

esch

-0.06

 calculations

-0.06

,)↵

-0.06

 terrifying

-0.06

ible

-0.06

POSITIVE LOGITS

 postId

0.08

.se

0.07

 अपर

0.07

�

0.06

DataSet

0.06

 STDMETHOD

0.06

Var

0.06

Nome

0.06

 groupId

0.06

ounge

0.06

Activations Density 0.123%

after

The neuron flags temporal markers of something occurring afterward—words like “after,” “aftermath,” and related tokens indicating “following” events.

No Comments

No Known Activations

after

The neuron flags temporal markers of something occurring afterward—words like “after,” “aftermath,” and related tokens indicating “following” events.

No Comments

No Known Activations