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. 87105
    Prev
    Next
    INDEX
    Explanations

    to

    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
     relieved
    -0.08
     mushroom
    -0.07
    _Total
    -0.07
    Y
    -0.07
     가능한
    -0.06
    straight
    -0.06
     stabilized
    -0.06
     alcuni
    -0.06
     Kültür
    -0.06
     laser
    -0.06
    POSITIVE LOGITS
     preprocess
    0.07
    .args
    0.07
    You
    0.06
     Terraria
    0.06
    Coord
    0.06
    odash
    0.06
     scarcity
    0.06
    ened
    0.06
     Coordinates
    0.06
     huyện
    0.06
    Activations Density 0.006%

    No Known Activations