INDEX

Explanations

Technical processes

np_max-act · gemini-2.0-flash

The neuron primarily lights up on numeric measurements and specifications (e.g. figures, dimensions, and related numeric details).

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

 foul

-0.07

 Buckley

-0.07

ForResource

-0.06

.highlight

-0.06

.bt

-0.06

 repeatedly

-0.06

 gras

-0.06

_predicate

-0.06

generated

-0.06

주소

-0.06

POSITIVE LOGITS

?");↵

0.07

_MIN

0.06

(Device

0.06

 textBox

0.06

,x

0.06

acular

0.06

.ov

0.06

='"+

0.06

[ix

0.06

 [])↵

0.06

Activations Density 0.107%

Technical processes

The neuron primarily lights up on numeric measurements and specifications (e.g. figures, dimensions, and related numeric details).

No Comments

No Known Activations

Technical processes

The neuron primarily lights up on numeric measurements and specifications (e.g. figures, dimensions, and related numeric details).

No Comments

No Known Activations