© 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. 27-RESID-POST-AA
    11. 22910
    Prev
    Next
    INDEX
    Explanations

    say the ending ;

    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_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     weaponry
    -0.07
    .Helpers
    -0.06
    chas
    -0.06
     Breath
    -0.06
     heritage
    -0.06
    fav
    -0.06
     Veterans
    -0.06
    _archive
    -0.06
    .Master
    -0.06
    -case
    -0.06
    POSITIVE LOGITS
    ZeroWidthSpace
    0.06
     MÜ
    0.06
     реб
    0.06
    rightarrow
    0.06
     Chicken
    0.06
     københavn
    0.06
     birlikte
    0.06
    awei
    0.06
    γέν
    0.06
    (className
    0.06
    Activations Density 0.015%

    No Known Activations