© 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. 11-RESID-POST-AA
    11. 47022
    Prev
    Next
    INDEX
    Explanations

    generics

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    継
    -0.07
     Ở
    -0.07
    ーネ
    -0.06
    WithIdentifier
    -0.06
    sınız
    -0.06
     tại
    -0.06
     bölüm
    -0.06
     แล
    -0.06
    <J
    -0.06
    stell
    -0.06
    POSITIVE LOGITS
    .mods
    0.07
     verificar
    0.07
    анси
    0.07
     }):
    0.07
    575
    0.07
     RHS
    0.06
    ória
    0.06
     toxin
    0.06
    ώς
    0.06
    ileges
    0.06
    Activations Density 0.003%

    No Known Activations