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. 87104
    Prev
    Next
    INDEX
    Explanations

    is

    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
    对方
    -0.06
     канди
    -0.06
    ケース
    -0.06
     ISI
    -0.06
    iris
    -0.06
     tighten
    -0.06
     reass
    -0.06
    nop
    -0.06
    acho
    -0.06
     admon
    -0.06
    POSITIVE LOGITS
    ฤษ
    0.07
     WALL
    0.07
    .Sequential
    0.07
     restarting
    0.07
    shutdown
    0.07
     escal
    0.07
    通常
    0.06
     textured
    0.06
     суд
    0.06
     Saves
    0.06
    Activations Density 0.079%

    No Known Activations