© 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. 19-RESID-POST-AA
    11. 87370
    Prev
    Next
    INDEX
    Explanations

    fantasy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,J
    -0.06
    _attrs
    -0.06
    _fig
    -0.06
     yr
    -0.06
     webView
    -0.06
    ourcing
    -0.06
    emic
    -0.06
     Nurse
    -0.06
     fixation
    -0.06
    asje
    -0.05
    POSITIVE LOGITS
     применения
    0.07
    QA
    0.07
     Magic
    0.07
     almak
    0.07
     conta
    0.07
    .travel
    0.06
     comida
    0.06
     fantasy
    0.06
     ειδ
    0.06
     INTERNAL
    0.06
    Activations Density 0.007%

    No Known Activations