INDEX

Explanations

is

np_max-act · gemini-2.0-flash

This neuron detects generic evaluative statements about a company’s strategic positioning, especially phrases like “it is well positioned to…”

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

covers

-0.06

 ním

-0.06

 succinct

-0.06

מ

-0.06

_agg

-0.06

pled

-0.06

amespace

-0.06

avings

-0.06

 Cater

-0.06

.called

-0.05

POSITIVE LOGITS

issional

0.07

 осві

0.07

 Mỹ

0.06

 Venom

0.06

 profes

0.06

ī

0.06

桌

0.06

Yus

0.06

IEW

0.06

卓

0.06

Activations Density 0.034%

is

This neuron detects generic evaluative statements about a company’s strategic positioning, especially phrases like “it is well positioned to…”

No Comments

No Known Activations