INDEX

Explanations

Counterfeiting

np_max-act · gemini-2.0-flash

This neuron detects words related to counterfeiting and forgery.

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

.Ui

-0.07

接

-0.06

sys

-0.06

bě

-0.06

 nằm

-0.06

能

-0.06

 ukon

-0.06

Sea

-0.06

Reload

-0.06

POSITIVE LOGITS

aturated

0.07

eri

0.07

 Claud

0.07

 analyst

0.07

 >↵

0.07

hey

0.07

 Natalie

0.06

 Pharm

0.06

[image

0.06

baar

0.06

Activations Density 0.005%

Counterfeiting

This neuron detects words related to counterfeiting and forgery.

No Comments

No Known Activations