INDEX

Explanations

you/your

np_max-act · gemini-2.0-flash

The neuron is detecting the word “you” (i.e. the second‐person pronoun).

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

Amazon

-0.08

FTP

-0.07

开放

-0.07

 subdivision

-0.07

tas

-0.06

小说

-0.06

yt

-0.06

同步

-0.06

Img

-0.06

SYNC

-0.06

POSITIVE LOGITS

 депут

0.07

(button

0.07

 Dân

0.07

>User

0.07

 lesen

0.06

 протяж

0.06

 RECE

0.06

九

0.06

`,↵

0.06

πουργ

0.06

Activations Density 0.051%

you/your

The neuron is detecting the word “you” (i.e. the second‐person pronoun).

No Comments

No Known Activations

you/your

The neuron is detecting the word “you” (i.e. the second‐person pronoun).

No Comments

No Known Activations