© 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. 19-RESID-POST-AA
    11. 125143
    Prev
    Next
    INDEX
    Explanations

    detecting malicious content

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     particul
    -0.06
    >f
    -0.06
    _Global
    -0.06
    (code
    -0.06
     smack
    -0.06
    ित
    -0.05
    errmsg
    -0.05
     whirl
    -0.05
    _vocab
    -0.05
    (px
    -0.05
    POSITIVE LOGITS
     پرس
    0.07
     Cannon
    0.07
    ประม
    0.06
    addOn
    0.06
     Schumer
    0.06
     scrollbar
    0.06
    跟
    0.06
    .GONE
    0.06
     Volunteer
    0.06
     Gree
    0.06
    Activations Density 0.049%

    No Known Activations