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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 32256
    Prev
    Next
    INDEX
    Explanations

    >

    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
    [table
    -0.07
    ونت
    -0.06
    つけ
    -0.06
    ивши
    -0.06
    vido
    -0.06
     حذ
    -0.06
    觉得
    -0.06
    721
    -0.06
    ieving
    -0.06
    -Assad
    -0.06
    POSITIVE LOGITS
    umped
    0.07
    まれ
    0.07
     lã
    0.07
    >
    0.07
    _undo
    0.06
     Cheap
    0.06
    (series
    0.06
    coordinates
    0.06
     Demonstr
    0.06
    拉
    0.06
    Activations Density 0.015%

    No Known Activations