INDEX

Explanations

A

np_max-act · gemini-2.0-flash

This neuron responds to uppercase multi‐letter acronyms or initialisms (e.g., organization names).

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

blend

-0.07

 Denver

-0.06

.lines

-0.06

 крови

-0.06

 закон

-0.06

_mpi

-0.06

_paper

-0.06

volt

-0.06

 turno

-0.06

 paramName

-0.06

POSITIVE LOGITS

ar

0.07

 mAuth

0.07

styled

0.06

روط

0.06

userID

0.06

MethodImpl

0.06

orra

0.06

 نادي

0.06

 तल

0.06

Activations Density 0.059%

A

This neuron responds to uppercase multi‐letter acronyms or initialisms (e.g., organization names).

No Comments

No Known Activations