© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 26893
    Prev
    Next
    INDEX
    Explanations

    procedures or methods

    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
     a
    -0.08
    uddled
    -0.08
    'A
    -0.08
    nerg
    -0.07
     A
    -0.07
     A
    -0.07
    oloji
    -0.07
     an
    -0.07
    від
    -0.07
     ber
    -0.07
    POSITIVE LOGITS
    ambre
    0.07
    /database
    0.06
    CONTEXT
    0.06
    gamber
    0.06
    の人
    0.06
     dile
    0.06
    _Context
    0.06
     tờ
    0.06
     шаг
    0.06
    ्ट
    0.06
    Activations Density 0.031%

    No Known Activations