© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 6891
    Prev
    Next
    INDEX
    Explanations

    once

    np_max-act · gemini-2.0-flash

    This neuron detects the “once” in `#pragma once` header‐guard directives.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    за
    -0.06
    prog
    -0.06
     wig
    -0.06
     clim
    -0.06
    QP
    -0.06
     даних
    -0.06
    cstdio
    -0.06
     imitation
    -0.06
    filtr
    -0.06
    ologia
    -0.06
    POSITIVE LOGITS
     jour
    0.07
     OnDestroy
    0.07
    "}↵
    0.07
    _upd
    0.07
    .land
    0.06
     rond
    0.06
     Waterloo
    0.06
     speeds
    0.06
     Emmy
    0.06
    _major
    0.06
    Activations Density 0.000%

    No Known Activations