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. 87039
    Prev
    Next
    INDEX
    Explanations

    Physics/Engineering

    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
     poetic
    -0.07
    rdf
    -0.06
    ertime
    -0.06
    	Color
    -0.06
    fuse
    -0.06
    untlet
    -0.06
     Size
    -0.06
    Timer
    -0.06
     Weaver
    -0.06
     scientific
    -0.06
    POSITIVE LOGITS
    +"<
    0.06
    anggan
    0.06
    电子
    0.06
    ÖL
    0.06
    .dgv
    0.06
    ."&
    0.06
     $('<
    0.06
    STIT
    0.06
    habit
    0.06
    /",↵
    0.06
    Activations Density 0.071%

    No Known Activations