INDEX

Explanations

Explaining specific details

np_max-act · gemini-2.0-flash

The neuron detects discussion of production or synthesis processes (e.g. mentions of “production,” “process,” “synthesis,” etc.).

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

·

-0.06

 Wenger

-0.06

necessary

-0.06

 Hint

-0.06

、それ

-0.06

////////////////////////////////////////////////////////////////////////////////↵↵

-0.06

Pooling

-0.06

era

-0.06

 Plenty

-0.06

ッカー

-0.06

POSITIVE LOGITS

.an

0.06

Towards

0.06

 Towards

0.06

 annot

0.06

 supern

0.06

社区

0.06

рок

0.06

 Transitional

0.06

 sucht

0.06

(lang

0.06

Activations Density 0.047%

Explaining specific details

The neuron detects discussion of production or synthesis processes (e.g. mentions of “production,” “process,” “synthesis,” etc.).

No Comments

No Known Activations