INDEX

Explanations

(_

np_max-act · gemini-2.0-flash

This neuron detects occurrences of the Swift keyword “in,” as used in function parameter clauses and closure 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

ossier

-0.07

,List

-0.06

爸

-0.06

Cha

-0.06

OPS

-0.06

eth

-0.06

(ap

-0.06

 osob

-0.06

/work

-0.06

Longitude

-0.06

POSITIVE LOGITS

vendor

0.07

|_

0.07

ratings

0.07

 midfield

0.07

webkit

0.07

نگی

0.06

自动

0.06

 haul

0.06

 "','

0.06

 meno

0.06

Activations Density 0.001%

(_

This neuron detects occurrences of the Swift keyword “in,” as used in function parameter clauses and closure headers.

No Comments

No Known Activations