INDEX

Explanations

medical cases

np_max-act · gemini-2.0-flash

The neuron is picking out tokens that mark temporal progression or sequence in a medical case narrative (e.g. “after,” “days,” “then,” “later”).

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

 زی

-0.06

_workflow

-0.06

_merged

-0.06

 возраста

-0.06

膜

-0.06

 yönetic

-0.06

şa

-0.06

 Pool

-0.06

かけ

-0.05

 모습

-0.05

POSITIVE LOGITS

ervers

0.07

vue

0.07

ASM

0.07

 stumbled

0.07

inite

0.07

OVE

0.07

 Filename

0.06

 دهند

0.06

WWW

0.06

ami

0.06

Activations Density 0.018%

medical cases

The neuron is picking out tokens that mark temporal progression or sequence in a medical case narrative (e.g. “after,” “days,” “then,” “later”).

No Comments

No Known Activations

medical cases

The neuron is picking out tokens that mark temporal progression or sequence in a medical case narrative (e.g. “after,” “days,” “then,” “later”).

No Comments

No Known Activations