© 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. 107248
    Prev
    Next
    INDEX
    Explanations

    strange characters

    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
    ——
    -0.07
     hot
    -0.06
    IfNeeded
    -0.06
    fila
    -0.06
    Ky
    -0.06
    ITTLE
    -0.06
    ceed
    -0.06
     CROSS
    -0.06
    團
    -0.06
    aptured
    -0.06
    POSITIVE LOGITS
     chaired
    0.07
     nghĩa
    0.06
    aying
    0.06
     legitimacy
    0.06
    /en
    0.06
     wildlife
    0.06
     cins
    0.06
    authorize
    0.06
     riêng
    0.06
    نگی
    0.06
    Activations Density 0.000%

    No Known Activations