INDEX

Explanations

data manipulation

np_max-act · gemini-2.0-flash

This neuron identifies keywords and phrases that signal clustering or grouping instructions (e.g., "cluster," "phrases," "following," "similar").

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

	char

-0.08

.paging

-0.07

�

-0.07

acent

-0.06

 yards

-0.06

puty

-0.06

cba

-0.06

εξ

-0.06

 assembling

-0.06

(port

-0.06

POSITIVE LOGITS

стро

0.07

 getString

0.07

URIComponent

0.06

ZERO

0.06

 ustanov

0.06

 особливо

0.06

rights

0.06

주는

0.06

 nostalg

0.06

Dyn

0.06

Activations Density 0.043%

data manipulation

This neuron identifies keywords and phrases that signal clustering or grouping instructions (e.g., "cluster," "phrases," "following," "similar").

No Comments

No Known Activations

data manipulation

This neuron identifies keywords and phrases that signal clustering or grouping instructions (e.g., "cluster," "phrases," "following," "similar").

No Comments

No Known Activations