INDEX

Explanations

Back

np_max-act · gemini-2.0-flash

The neuron flags mentions of clock “hands” (in particular the “hour” and “minute” hand).

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

 Plugin

-0.06

rac

-0.06

 Trojan

-0.06

util

-0.06

clusters

-0.06

 Arch

-0.06

 Proud

-0.06

List

-0.06

translator

-0.06

ố

-0.06

POSITIVE LOGITS

RIORITY

0.07

(renderer

0.06

마다

0.06

:v

0.06

 rage

0.06

've

0.06

 sermon

0.06

ヾ

0.06

btc

0.06

 coward

0.06

Activations Density 0.134%

Back

The neuron flags mentions of clock “hands” (in particular the “hour” and “minute” hand).

No Comments

No Known Activations