© 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. 39213
    Prev
    Next
    INDEX
    Explanations

    court documents

    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
     Oven
    -0.07
    336
    -0.07
     quanh
    -0.06
    .WRITE
    -0.06
    (commands
    -0.06
     opioid
    -0.06
    相信
    -0.06
     umožňuje
    -0.06
    ازد
    -0.06
     Battlefield
    -0.06
    POSITIVE LOGITS
     Хар
    0.07
     GB
    0.06
    avel
    0.06
     allele
    0.06
    sorry
    0.06
     costs
    0.06
     Expr
    0.06
     Yi
    0.06
    total
    0.06
    .seq
    0.06
    Activations Density 0.000%

    No Known Activations