INDEX

Explanations

education

np_max-act · gemini-2.0-flash

This neuron activates on terms related to special education and its professional context (e.g., special education, related services, and the names of specialists).

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

_ch

-0.07

FieldType

-0.06

 validar

-0.06

 кан

-0.06

_tex

-0.06

UW

-0.06

okud

-0.06

ิทยา

-0.06

_am

-0.06

 Witch

-0.06

POSITIVE LOGITS

-sizing

0.08

curities

0.08

sue

0.07

 videa

0.07

 withdrawing

0.07

 spare

0.07

ano

0.07

Scr

0.07

-rated

0.06

udit

0.06

Activations Density 0.010%

education

This neuron activates on terms related to special education and its professional context (e.g., special education, related services, and the names of specialists).

No Comments

No Known Activations

education

This neuron activates on terms related to special education and its professional context (e.g., special education, related services, and the names of specialists).

No Comments

No Known Activations