© 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
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 52028
    Prev
    Next
    INDEX
    Explanations

    TCP sockets

    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
    <D
    -0.07
     引
    -0.07
    choice
    -0.06
    currentIndex
    -0.06
    _AF
    -0.06
    Et
    -0.06
     дис
    -0.06
    gd
    -0.06
     انت
    -0.06
    čně
    -0.06
    POSITIVE LOGITS
     серпня
    0.07
    ницы
    0.06
     seeking
    0.06
    лич
    0.06
    .RowStyle
    0.06
    £o
    0.06
     листопада
    0.06
    [len
    0.06
     Performing
    0.06
     Box
    0.06
    Activations Density 0.025%

    No Known Activations