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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 73059
    Prev
    Next
    INDEX
    Explanations

    development

    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
    unicode
    -0.07
     YORK
    -0.06
    -med
    -0.06
     devil
    -0.06
    措
    -0.06
    gaard
    -0.06
     mistr
    -0.06
    ram
    -0.06
     zast
    -0.06
    _res
    -0.06
    POSITIVE LOGITS
     football
    0.07
    ―
    0.07
     inaccessible
    0.06
     자연
    0.06
    .setEnabled
    0.06
     auth
    0.06
     assessments
    0.06
    .cbo
    0.06
     userEmail
    0.06
     tops
    0.06
    Activations Density 0.001%

    No Known Activations