INDEX

Explanations

digits

np_max-act · gemini-2.0-flash

This neuron detects reference citation years (four‐digit publication years in brackets).

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

 Аль

-0.07

 Islanders

-0.07

 trousers

-0.06

	verify

-0.06

Marvel

-0.06

.tv

-0.06

 marvel

-0.06

 Appe

-0.06

及其

-0.06

 Bible

-0.06

POSITIVE LOGITS

 vegas

0.07

часно

0.07

0.06

 спас

0.06

etto

0.06

こ

0.06

OMETRY

0.06

ARDS

0.06

OPEN

0.06

ắc

0.06

Activations Density 0.011%

digits

This neuron detects reference citation years (four‐digit publication years in brackets).

No Comments

No Known Activations

digits

This neuron detects reference citation years (four‐digit publication years in brackets).

No Comments

No Known Activations