INDEX

Explanations

Returning/going somewhere

np_max-act · gemini-2.0-flash

The neuron activates on tokens in passages describing someone’s return or arrival back home—especially phrased as “returned to [place], where…”

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

 swimming

-0.07

.unsplash

-0.07

İŞ

-0.07

 γνω

-0.06

 nota

-0.06

카라

-0.06

caffe

-0.06

rolling

-0.06

 Care

-0.06

 SNAP

-0.06

POSITIVE LOGITS

0.07

литель

0.06

 stringBy

0.06

ATEGY

0.06

 đều

0.06

 Prepared

0.06

toggle

0.06

Activations Density 0.048%

Returning/going somewhere

The neuron activates on tokens in passages describing someone’s return or arrival back home—especially phrased as “returned to [place], where…”

No Comments

No Known Activations