INDEX

Explanations

Descriptive/opinionated writing

np_max-act · gemini-2.0-flash

This neuron fires strongly on longer, content-bearing words (i.e. non-function, domain-specific terms) rather than on short or common words.

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

meg

-0.07

PAD

-0.07

 сум

-0.06

itti

-0.06

설

-0.06

 melan

-0.06

 presume

-0.06

_POL

-0.06

.HCM

-0.06

实

-0.06

POSITIVE LOGITS

;amp

0.08

Units

0.07

-bootstrap

0.07

 QDateTime

0.07

 barn

0.07

sm

0.07

 đề

0.06

(^

0.06

ární

0.06


↵

↵

0.06

Activations Density 0.136%

Descriptive/opinionated writing

This neuron fires strongly on longer, content-bearing words (i.e. non-function, domain-specific terms) rather than on short or common words.

No Comments

No Known Activations