© 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. 23-RESID-POST-AA
    11. 67500
    Prev
    Next
    INDEX
    Explanations

    Cranium morphology

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    $client
    -0.07
     Loch
    -0.07
    商品
    -0.06
    booking
    -0.06
    refix
    -0.06
     misleading
    -0.06
    .Cons
    -0.06
    Normalized
    -0.06
    693
    -0.06
     Lies
    -0.06
    POSITIVE LOGITS
    _TOGGLE
    0.07
    笔
    0.06
    <|begin_of_text|>
    0.06
    يلة
    0.06
    SSID
    0.06
     digitalWrite
    0.06
    cken
    0.06
     일반
    0.06
    ++.
    0.05
    cripcion
    0.05
    Activations Density 0.029%

    No Known Activations