INDEX

Explanations

-model

np_max-act · gemini-2.0-flash

This neuron detects occurrences of binding directives that include “model” (e.g. ng-model or v-model).

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

orraine

-0.07

hub

-0.07

Sarah

-0.06

្�

-0.06

orghini

-0.06

 subtype

-0.06

разу

-0.06

Ram

-0.06

ramer

-0.06

�

-0.06

POSITIVE LOGITS

 false

0.07

:false

0.07

 wifi

0.07

 catch

0.07

]**

0.07

以为

0.07

 Whether

0.06

 avons

0.06

><?

0.06

 jedem

0.06

Activations Density 0.004%

-model

This neuron detects occurrences of binding directives that include “model” (e.g. ng-model or v-model).

No Comments

No Known Activations