INDEX

Explanations

canvas

np_max-act · gemini-2.0-flash

The neuron activates strongly on the word “Canvas,” i.e. it detects occurrences of the term “canvas” in the text.

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

rte

-0.08

bishop

-0.07

 strtol

-0.07

 Superior

-0.07

wort

-0.07

.Enc

-0.07

 Earl

-0.07

 sortOrder

-0.07

 lieutenant

-0.07

lok

-0.07

POSITIVE LOGITS

 Canvas

0.14

Canvas

0.11

 canvas

0.10

canvas

0.10

	canvas

0.09

 cans

0.08

_canvas

0.08

zej

0.08

avi

0.08

 canv

0.07

Activations Density 0.004%

canvas

The neuron activates strongly on the word “Canvas,” i.e. it detects occurrences of the term “canvas” in the text.

No Comments

No Known Activations