© 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. 85747
    Prev
    Next
    INDEX
    Explanations

    regulated

    np_max-act · gemini-2.0-flash

    This neuron responds to terms describing regulatory or modulatory processes (e.g., “regulation,” “regulated,” “modified,” “by”) in molecular biology contexts.

    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
     dragged
    -0.07
     employee
    -0.06
    351
    -0.06
    ์เซ
    -0.06
    根
    -0.06
     salads
    -0.06
    ，因
    -0.06
    QObject
    -0.06
     spectra
    -0.06
    lik
    -0.05
    POSITIVE LOGITS
    .timeline
    0.07
    NF
    0.06
    Phi
    0.06
     Transit
    0.06
     Xuân
    0.06
    TRGL
    0.06
    P
    0.06
     روش
    0.06
     đ
    0.06
    :.:.:
    0.06
    Activations Density 0.048%

    No Known Activations