© 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 EvalsExportsAPI 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. 66516
    Prev
    Next
    INDEX
    Explanations

    minority

    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
    (js
    -0.07
    /loader
    -0.07
    edriver
    -0.06
    ţ
    -0.06
    ț
    -0.06
    бач
    -0.06
     HBO
    -0.06
     Πρό
    -0.06
    ...",↵
    -0.06
     wy
    -0.06
    POSITIVE LOGITS
     minority
    0.08
    onto
    0.07
     Minority
    0.07
    ulses
    0.07
    _G
    0.07
     щось
    0.07
     Sammy
    0.06
     Dio
    0.06
     minorities
    0.06
     Benghazi
    0.06
    Activations Density 0.003%

    No Known Activations