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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 13282
    Prev
    Next
    INDEX
    Explanations

    population statistics

    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
    Communication
    -0.07
     innoc
    -0.06
     Ottawa
    -0.06
    pixel
    -0.06
    ира
    -0.06
    .Panel
    -0.06
     Bishop
    -0.06
     škola
    -0.06
     Kumar
    -0.06
     nối
    -0.06
    POSITIVE LOGITS
     ".$_
    0.06
    _ENUM
    0.06
    (parsed
    0.06
    _RW
    0.06
    jedn
    0.06
    even
    0.06
     Ult
    0.06
     musel
    0.06
    _actor
    0.06
    [cell
    0.05
    Activations Density 0.012%

    No Known Activations