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. 20431
    Prev
    Next
    INDEX
    Explanations

    code and equations

    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
     einer
    -0.06
     juxtap
    -0.06
     fins
    -0.06
     covering
    -0.06
     cinemas
    -0.06
     fixtures
    -0.06
    amphetamine
    -0.06
     Bul
    -0.06
    separator
    -0.06
     reconciliation
    -0.05
    POSITIVE LOGITS
     />,
    0.07
     ISSN
    0.07
     Например
    0.07
     _____
    0.07
     الم
    0.06
    adoo
    0.06
    "][
    0.06
    _PROXY
    0.06
     cuff
    0.06
     )"
    0.06
    Activations Density 0.131%

    No Known Activations