INDEX

Explanations

Travel

np_max-act · gemini-2.0-flash

The neuron fires on tokens indicating a requested trip duration or time period (e.g. “three week,” “3 day,” “10 days”).

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

 thugs

-0.06

رح

-0.06

opencv

-0.06

 BOTH

-0.06

 PyTuple

-0.06

्रथ

-0.06

�

-0.06

LEVEL

-0.06

 opioid

-0.06

 частини

-0.06

POSITIVE LOGITS

ually

0.07

astically

0.06

{-

0.06

@SuppressWarnings

0.06

SessionFactory

0.06

gr

0.06

chematic

0.06

_REMOVE

0.06

 Initialized

0.06

elly

0.06

Activations Density 0.096%

Travel

The neuron fires on tokens indicating a requested trip duration or time period (e.g. “three week,” “3 day,” “10 days”).

No Comments

No Known Activations