© 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. 15-RESID-POST-AA
    11. 127453
    Prev
    Next
    INDEX
    Explanations

    Introductions

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (DataType
    -0.07
    .navigate
    -0.07
     Pron
    -0.06
     App
    -0.06
     parametros
    -0.06
    FINE
    -0.06
     Blind
    -0.06
    (subject
    -0.06
     مادر
    -0.06
    .modify
    -0.06
    POSITIVE LOGITS
     grup
    0.06
     Liter
    0.06
     तक
    0.06
    _TAGS
    0.06
    ucci
    0.06
    ​​
    0.06
    .getInputStream
    0.06
     partially
    0.05
    .lon
    0.05
    -ul
    0.05
    Activations Density 0.087%

    No Known Activations