INDEX

Explanations

numbers

np_max-act · gemini-2.0-flash

This neuron fires on LaTeX‐style mathematical content (e.g. “\sum,” “\frac,” superscripts/subscripts, and variable‐or number tokens inside math).

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

�

-0.06

こう

-0.06

}.${

-0.06

awning

-0.06

 Fluid

-0.06

Had

-0.06

domains

-0.05

 nêu

-0.05

 Sala

-0.05

 belum

-0.05

POSITIVE LOGITS

五月

0.07

 ',',

0.07

 Αθή

0.06

 Респ

0.06

��

0.06

 traj

0.06

HE

0.06

.HORIZONTAL

0.06

 halfway

0.06

 gratuites

0.06

Activations Density 0.017%

numbers

This neuron fires on LaTeX‐style mathematical content (e.g. “\sum,” “\frac,” superscripts/subscripts, and variable‐or number tokens inside math).

No Comments

No Known Activations

numbers

This neuron fires on LaTeX‐style mathematical content (e.g. “\sum,” “\frac,” superscripts/subscripts, and variable‐or number tokens inside math).

No Comments

No Known Activations