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. 87108
    Prev
    Next
    INDEX
    Explanations

    owners

    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
    iculo
    -0.07
    _norm
    -0.07
    emplo
    -0.07
    63
    -0.06
     videot
    -0.06
    WIDTH
    -0.06
    (dot
    -0.06
    Spider
    -0.06
     Gospel
    -0.06
    pendicular
    -0.06
    POSITIVE LOGITS
     really
    0.07
     ASM
    0.07
     Covers
    0.07
    .fileName
    0.07
    -assets
    0.07
    (clean
    0.06
     responsable
    0.06
    osci
    0.06
     SqlCommand
    0.06
    Discover
    0.06
    Activations Density 0.003%

    No Known Activations