INDEX

Explanations

Continue/Read More prompts

np_max-act · gemini-2.0-flash

This neuron detects “read more” or “continue reading” link prompts (e.g. “Read More,” “Continue Reading,” etc.).

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

isNull

-0.07

heap

-0.06

 yuan

-0.06

徐

-0.06

 разм

-0.06

 Delaware

-0.06

_ATTRIBUTES

-0.06

-wheel

-0.06

_CONNECTED

-0.06

�

-0.06

POSITIVE LOGITS

 joystick

0.07

 Lilly

0.07

ungi

0.07

*****/↵

0.06

{s

0.06

&m

0.06

\F

0.06

department

0.06

stations

0.06

QN

0.06

Activations Density 0.007%

Continue/Read More prompts

This neuron detects “read more” or “continue reading” link prompts (e.g. “Read More,” “Continue Reading,” etc.).

No Comments

No Known Activations