INDEX

Explanations

See

np_max-act · gemini-2.0-flash

This neuron detects occurrences of the phrase “See the” (as in “See the NOTICE file…”) in comment headers.

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

ук

-0.07

‌تر

-0.07

 الدول

-0.06

flag

-0.06

 기억

-0.06

 Redemption

-0.06

Boot

-0.06

Severity

-0.06

 pouch

-0.06

 Imaging

-0.06

POSITIVE LOGITS

.NORTH

0.07

 relocated

0.06

<boolean

0.06

('_

0.06

.openqa

0.06

.ordinal

0.06

년에는

0.06

شنبه

0.06

的是

0.06

/black

0.06

Activations Density 0.001%

See

This neuron detects occurrences of the phrase “See the” (as in “See the NOTICE file…”) in comment headers.

No Comments

No Known Activations