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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 12036
    Prev
    Next
    INDEX
    Explanations

    hands

    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
     corporation
    -0.07
    gas
    -0.07
    Phi
    -0.07
     Cinema
    -0.07
    Bear
    -0.06
     illuminate
    -0.06
     rail
    -0.06
    antino
    -0.06
    サービス
    -0.06
     perí
    -0.06
    POSITIVE LOGITS
     hands
    0.08
    %).
    0.07
     errorHandler
    0.07
    lıklı
    0.06
    +='<
    0.06
     �
    0.06
     hand
    0.06
     руках
    0.06
    adresse
    0.06
    께서
    0.06
    Activations Density 0.037%

    No Known Activations