INDEX

Explanations

lex

np_max-act · gemini-2.0-flash

This neuron detects occurrences of the term “dyslexia” (and its morphological variants like dyslexic).

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

.OnItemClickListener

-0.07

DialogTitle

-0.06

製

-0.06

"T

-0.06

 sample

-0.06

==(

-0.06

os

-0.06

km

-0.06

Mac

-0.06

 Legislative

-0.05

POSITIVE LOGITS

0.07

 Refugee

0.07

 celib

0.07

 additives

0.07

Depending

0.06

 positioned

0.06

BSD

0.06

 пораж

0.06

ori

0.06

ictor

0.06

Activations Density 0.003%

lex

This neuron detects occurrences of the term “dyslexia” (and its morphological variants like dyslexic).

No Comments

No Known Activations