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. 78696
    Prev
    Next
    INDEX
    Explanations

    sports announcements and quotes

    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
    TableName
    -0.07
     Main
    -0.07
    係
    -0.06
    cw
    -0.06
     twee
    -0.06
    March
    -0.06
    !*
    -0.06
    一緒
    -0.06
     concess
    -0.06
    Entry
    -0.06
    POSITIVE LOGITS
     指
    0.07
    _qu
    0.07
    ETA
    0.06
    /class
    0.06
    calls
    0.06
     WON
    0.06
     dlouho
    0.06
     PHP
    0.06
     Ry
    0.06
    (tuple
    0.06
    Activations Density 0.034%

    No Known Activations