INDEX

Explanations

las

np_max-act · gemini-2.0-flash

This neuron detects occurrences of the term “neoplasm” (and its variants like “neoplasms” or “neoplasia”), i.e. cancer-related words.

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

 раздел

-0.07

 derin

-0.07

(strtolower

-0.07

rvé

-0.07

 yOffset

-0.06

_FIXED

-0.06

Salt

-0.06

็กหญ

-0.06

UserDefaults

-0.06

POSITIVE LOGITS

 implication

0.07

MAS

0.07

 πρα

0.07

 weapons

0.07

OUS

0.07

 nests

0.06

lean

0.06

etermined

0.06

las

0.06

cas

0.06

Activations Density 0.001%

las

This neuron detects occurrences of the term “neoplasm” (and its variants like “neoplasms” or “neoplasia”), i.e. cancer-related words.

No Comments

No Known Activations