INDEX

Explanations

Number lists

np_max-act · gemini-2.0-flash

The neuron primarily activates on numeric tokens (digits or multi-digit numbers).

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

igrationBuilder

-0.06

.Namespace

-0.06

MP

-0.06

DMA

-0.06

ToShow

-0.06

 Shades

-0.06

 codec

-0.06

 jejichž

-0.06

 ParameterDirection

-0.06

POSITIVE LOGITS

-major

0.07

壓

0.07

 escalated

0.06

_PATCH

0.06

 sacrifice

0.06

 stepped

0.06

ráci

0.06

 configured

0.06

수가

0.06

 Prosec

0.06

Activations Density 0.006%

Number lists

The neuron primarily activates on numeric tokens (digits or multi-digit numbers).

No Comments

No Known Activations