© 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. 15-RESID-POST-AA
    6. 26775
    Prev
    Next
    INDEX
    Explanations

    is,

    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
     реч
    -0.06
    Hour
    -0.06
     inaugural
    -0.06
    ��
    -0.06
     €
    -0.06
     getField
    -0.06
     Bellev
    -0.06
    ょう
    -0.06
     Assert
    -0.06
    Instructions
    -0.06
    POSITIVE LOGITS
    食品
    0.07
     tweaks
    0.06
    /User
    0.06
    _forms
    0.06
    .admin
    0.06
     acquaintance
    0.06
    ρός
    0.06
    딩
    0.06
    _neighbors
    0.06
    _sep
    0.06
    Activations Density 0.004%

    No Known Activations