© 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. 34163
    Prev
    Next
    INDEX
    Explanations

    Asking the time

    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
    λέον
    -0.06
    _optional
    -0.06
    allocator
    -0.06
     бюдж
    -0.06
     Bale
    -0.06
     tijd
    -0.06
     misdemean
    -0.06
    .UseText
    -0.06
    .optional
    -0.06
    _VAR
    -0.06
    POSITIVE LOGITS
    conduct
    0.07
     Th
    0.07
    ード
    0.06
    ewing
    0.06
    VERY
    0.06
     Bu
    0.06
    broker
    0.06
     advances
    0.06
    лении
    0.06
    DOM
    0.06
    Activations Density 0.004%

    No Known Activations