INDEX

Explanations

stating/quoting

np_max-act · gemini-2.0-flash

This neuron detects citations or attributions—mentions of an author or observer’s name together with reporting verbs (e.g. “writes,” “observed,” “states”).

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

amarin

-0.07

 kraje

-0.06

SFML

-0.06

gaard

-0.06

fra

-0.06

 ZeroConstructor

-0.06

.Record

-0.06

 renamed

-0.06

(Dictionary

-0.06

SPA

-0.06

POSITIVE LOGITS

otto

0.07

bon

0.07

 robert

0.06

bif

0.06

 Ways

0.06

 multiprocessing

0.06

.alibaba

0.06

 banc

0.06

STD

0.06

 grind

0.06

Activations Density 0.023%

stating/quoting

This neuron detects citations or attributions—mentions of an author or observer’s name together with reporting verbs (e.g. “writes,” “observed,” “states”).

No Comments

No Known Activations