Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 87031
    Prev
    Next
    INDEX
    Explanations

    /meta

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .↵↵↵
    -0.07
    .buy
    -0.07
    Contr
    -0.06
     transporter
    -0.06
    fortune
    -0.06
    ottes
    -0.06
     přech
    -0.06
    idon
    -0.06
     Purs
    -0.06
    Indent
    -0.06
    POSITIVE LOGITS
    /meta
    0.09
     молод
    0.08
     mělo
    0.07
     �
    0.07
    봐
    0.06
     inspire
    0.06
     Ge
    0.06
     Tarif
    0.06
    /demo
    0.06
     QVBoxLayout
    0.06
    Activations Density 0.000%

    No Known Activations