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. 15-RESID-POST-AA
    6. 114457
    Prev
    Next
    INDEX
    Explanations

    sports cars

    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
    Teachers
    -0.07
    hal
    -0.07
     rock
    -0.07
     Ethi
    -0.07
     Haley
    -0.06
     FOUND
    -0.06
     Э
    -0.06
     minY
    -0.06
    Campo
    -0.06
     OUTER
    -0.06
    POSITIVE LOGITS
     آزمون
    0.07
    emean
    0.07
    _EQ
    0.07
    UserID
    0.07
    prevent
    0.06
    .recycle
    0.06
     Bend
    0.06
    _png
    0.06
    ูล
    0.06
    pering
    0.06
    Activations Density 0.042%

    No Known Activations