INDEX

Explanations

step-by-step instructions

np_max-act · gemini-2.0-flash

This neuron never fires on any token—it’s effectively “dead” and 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

EEDED

-0.06

paration

-0.06

	flags

-0.06

(Spring

-0.06

wd

-0.06

Peak

-0.06

 surged

-0.06

maf

-0.06

ml

-0.06

>H

-0.06

POSITIVE LOGITS

 суспіль

0.07

.inspect

0.07

 fantast

0.07

_);↵↵

0.07

�

0.07

-del

0.06

 edeb

0.06

.NoArgsConstructor

0.06

 fellow

0.06

_hub

0.06

Activations Density 0.044%

step-by-step instructions

This neuron never fires on any token—it’s effectively “dead” and doesn’t detect any pattern.

No Comments

No Known Activations