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. 81037
    Prev
    Next
    INDEX
    Explanations

    espresso

    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
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     One
    -0.07
     caregivers
    -0.06
    .JComboBox
    -0.06
    末
    -0.06
    eses
    -0.06
    آن
    -0.06
    .Card
    -0.06
     Room
    -0.06
     arson
    -0.06
    verbosity
    -0.06
    POSITIVE LOGITS
     espresso
    0.08
     nonlinear
    0.07
     Certificate
    0.07
     Espresso
    0.07
     मजब
    0.07
    (wp
    0.07
    ,“
    0.06
    _DST
    0.06
    も
    0.06
    フ
    0.06
    Activations Density 0.003%

    No Known Activations