INDEX

Explanations

math and logic

np_max-act · gemini-2.0-flash

This neuron activates on occurrences of “number” (especially in phrases like “total number of …”) in mathematical reasoning or problem‐solving contexts.

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

Life

-0.07

_a

-0.06

MAX

-0.06

_SF

-0.06

Stan

-0.06

INSERT

-0.06

_mail

-0.06

Progress

-0.06

POSITIVE LOGITS

 některé

0.07

 вій

0.07

 istiyor

0.07

 دقیق

0.07

 νεφοκ

0.06

 filt

0.06

 Phương

0.06

 بیشتر

0.06

 Cumhuriyeti

0.06

 zamanda

0.06

Activations Density 0.046%

math and logic

This neuron activates on occurrences of “number” (especially in phrases like “total number of …”) in mathematical reasoning or problem‐solving contexts.

No Comments

No Known Activations