© 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. 15-RESID-POST-AA
    11. 27364
    Prev
    Next
    INDEX
    Explanations

    Mixed/non-standard text

    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
     ganze
    -0.06
    हम
    -0.06
    -instagram
    -0.06
     응
    -0.06
     brand
    -0.06
    بالإنجليزية
    -0.06
    marca
    -0.06
    massage
    -0.06
     jeune
    -0.06
    medical
    -0.06
    POSITIVE LOGITS
    _avail
    0.07
    読
    0.07
     Girlfriend
    0.06
     Generate
    0.06
     Pregn
    0.06
    (baseUrl
    0.06
     دی
    0.06
    @Enable
    0.06
    .Face
    0.06
    Init
    0.06
    Activations Density 0.001%

    No Known Activations