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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 113570
    Prev
    Next
    INDEX
    Explanations

    Manny

    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
    acro
    -0.08
     credible
    -0.07
    ovies
    -0.07
    subscription
    -0.06
     questo
    -0.06
     lorsque
    -0.06
    .UUID
    -0.06
    $date
    -0.06
    /comment
    -0.06
    _critical
    -0.06
    POSITIVE LOGITS
     Mans
    0.07
    Engine
    0.07
    .SetInt
    0.07
     Mann
    0.06
     Yan
    0.06
    на
    0.06
    NG
    0.06
     Mn
    0.06
     mansion
    0.06
    дн
    0.06
    Activations Density 0.021%

    No Known Activations