INDEX

Explanations

review

np_max-act · gemini-2.0-flash

This neuron detects in-text literature citations, particularly phrases pointing to reviews (e.g. “for review, see …”).

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

-0.07

یه

-0.07

 شرق

-0.06

up

-0.06

 Queue

-0.06

.Util

-0.06

IN

-0.06

 Share

-0.06

 pepper

-0.06

م

-0.06

POSITIVE LOGITS

Install

0.07

lify

0.07

[]>(

0.06

有什么

0.06

 필요

0.06

cf

0.06

ốn

0.06

&'

0.06

刺

0.06

encv

0.06

Activations Density 0.011%

review

This neuron detects in-text literature citations, particularly phrases pointing to reviews (e.g. “for review, see …”).

No Comments

No Known Activations

review

This neuron detects in-text literature citations, particularly phrases pointing to reviews (e.g. “for review, see …”).

No Comments

No Known Activations