INDEX

Explanations

numbers

np_max-act · gemini-2.0-flash

The main thing this neuron does is spot numeric tokens—especially multi‐digit figures like rankings, scores, and statistical counts.

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

proof

-0.06

 desar

-0.06

 decrypt

-0.06

 감독

-0.06

.inline

-0.06

оту

-0.06

計算

-0.05

xi

-0.05

 alguns

-0.05

POSITIVE LOGITS

 정책

0.07

(Target

0.06

모

0.06

ATEG

0.06

_ops

0.06

edata

0.06

 Kasich

0.06

.inner

0.06

\controllers

0.06

 yielding

0.06

Activations Density 0.007%

numbers

The main thing this neuron does is spot numeric tokens—especially multi‐digit figures like rankings, scores, and statistical counts.

No Comments

No Known Activations