© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 36966
    Prev
    Next
    INDEX
    Explanations

    code and technical documentation

    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
     ECB
    -0.06
     drinks
    -0.06
     CS
    -0.06
     charts
    -0.06
    .mass
    -0.06
    _cs
    -0.06
    meni
    -0.06
     rehabilitation
    -0.06
    .full
    -0.06
    Sw
    -0.06
    POSITIVE LOGITS
    working
    0.07
    icon
    0.06
     инструмент
    0.06
     invaluable
    0.06
     ik
    0.06
    _ln
    0.06
     blue
    0.06
     трех
    0.06
     IMPORTANT
    0.06
    ’ex
    0.06
    Activations Density 0.000%

    No Known Activations