Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 15-RESID-POST-AA
    6. 111376
    Prev
    Next
    INDEX
    Explanations

    F

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dön
    -0.06
    _peer
    -0.06
    enu
    -0.06
    _frequency
    -0.06
     recurring
    -0.06
    ²
    -0.06
    .borderColor
    -0.06
     Jord
    -0.06
     tendr
    -0.06
     quoi
    -0.06
    POSITIVE LOGITS
     Sunshine
    0.06
    places
    0.06
    /small
    0.06
    Updates
    0.06
    (csv
    0.06
    図
    0.06
    ews
    0.06
    Sheet
    0.06
    abytes
    0.06
    opes
    0.06
    Activations Density 0.002%

    No Known Activations