INDEX

Explanations

itors

np_max-act · gemini-2.0-flash

This neuron detects the “Competitors at the …” category labels (participation in specific sporting 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

sources

-0.07

PSG

-0.07

�

-0.06

_VE

-0.06

ifier

-0.06

_subtype

-0.06

Android

-0.06

时间

-0.06

/Open

-0.06

 су

-0.06

POSITIVE LOGITS

_hex

0.07

 Chiến

0.06

 accent

0.06

균

0.06

 elder

0.06

FRINGEMENT

0.06

こちら

0.06

 alım

0.06

 contentValues

0.06

 cling

0.06

Activations Density 0.001%

itors

This neuron detects the “Competitors at the …” category labels (participation in specific sporting events).

No Comments

No Known Activations