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. 87068
    Prev
    Next
    INDEX
    Explanations

    Code or website text

    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
     Remix
    -0.08
    Few
    -0.07
     mesmer
    -0.06
    Program
    -0.06
    需求
    -0.06
    rends
    -0.06
     textiles
    -0.06
     dank
    -0.06
    SEARCH
    -0.06
     helpless
    -0.06
    POSITIVE LOGITS
     millis
    0.07
    -coordinate
    0.07
     했다
    0.07
    jpg
    0.06
    *\
    0.06
    „N
    0.06
    (pad
    0.06
    *-
    0.06
     Ink
    0.06
    ámara
    0.06
    Activations Density 0.158%

    No Known Activations