© 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. 28027
    Prev
    Next
    INDEX
    Explanations

    noble

    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
    Question
    -0.07
     얼굴
    -0.07
    eday
    -0.07
    etten
    -0.07
     methane
    -0.07
    xBD
    -0.07
    gün
    -0.07
    \xf
    -0.06
    beta
    -0.06
    liquid
    -0.06
    POSITIVE LOGITS
     noble
    0.07
     lifelong
    0.07
     CultureInfo
    0.07
    护
    0.06
    нула
    0.06
    jas
    0.06
     notas
    0.06
    .signup
    0.06
    eresa
    0.06
    พระ
    0.06
    Activations Density 0.003%

    No Known Activations