INDEX

Explanations

risk

np_max-act · gemini-2.0-flash

The neuron activates for mentions of “risk” and especially risk‐level descriptors (e.g. high-risk, low-risk) in clinical 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

washing

-0.07

 Johann

-0.07

 Constantin

-0.07

 "":↵

-0.07

ago

-0.07

 classifiers

-0.07

çois

-0.06

ungal

-0.06

ett

-0.06

Qin

-0.06

POSITIVE LOGITS

탐

0.08

 dostup

0.07

 recount

0.07

 Result

0.06

 plagued

0.06

满

0.06

banks

0.06

.Prot

0.06

 beneficiaries

0.06

 第一

0.06

Activations Density 0.009%

risk

The neuron activates for mentions of “risk” and especially risk‐level descriptors (e.g. high-risk, low-risk) in clinical contexts.

No Comments

No Known Activations