INDEX

Explanations

fluent

np_max-act · gemini-2.0-flash

The neuron never responds to any tokens here—it appears to be inactive (i.e. it doesn’t detect any pattern).

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

pig

-0.07

 making

-0.06

ίος

-0.06

Kin

-0.06

 picked

-0.06

pis

-0.06

xba

-0.06

 underneath

-0.06

attery

-0.06

_is

-0.06

POSITIVE LOGITS

 fluent

0.11

uent

0.08

DSL

0.08

 Func

0.07

uen

0.07

 flask

0.07

;}

0.07

 Fluent

0.07

flux

0.07

	glfw

0.07

Activations Density 0.002%

fluent

The neuron never responds to any tokens here—it appears to be inactive (i.e. it doesn’t detect any pattern).

No Comments

No Known Activations

fluent

The neuron never responds to any tokens here—it appears to be inactive (i.e. it doesn’t detect any pattern).

No Comments

No Known Activations