INDEX

Explanations

forum posts

np_max-act · gemini-2.0-flash

The neuron flags subjective evaluative words—adjectives and adverbs that express opinion, judgment, or degree.

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

stdout

-0.07

"For

-0.07

 Robertson

-0.07

真正

-0.06

 Monter

-0.06

 Risk

-0.06

(('

-0.06

NSSet

-0.06

 risk

-0.06

 Лу

-0.06

POSITIVE LOGITS

した

0.07

мотря

0.06

 charts

0.06

 };
↵

0.06

imming

0.06

amy

0.06

Smooth

0.06

 supern

0.06

دا

0.06

 }};↵

0.05

Activations Density 0.025%

forum posts

The neuron flags subjective evaluative words—adjectives and adverbs that express opinion, judgment, or degree.

No Comments

No Known Activations

forum posts

The neuron flags subjective evaluative words—adjectives and adverbs that express opinion, judgment, or degree.

No Comments

No Known Activations