© 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. 11-RESID-POST-AA
    6. 24852
    Prev
    Next
    INDEX
    Explanations

    Theme

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     huyết
    -0.07
    ıcı
    -0.07
    imity
    -0.07
    iềm
    -0.07
    duto
    -0.07
     환산
    -0.07
    Founded
    -0.06
     Desde
    -0.06
     launched
    -0.06
     huku
    -0.06
    POSITIVE LOGITS
     TU
    0.07
    NW
    0.07
     appell
    0.07
    /community
    0.06
     топ
    0.06
    ebb
    0.06
     repetition
    0.06
     deriv
    0.06
    .track
    0.06
    插
    0.06
    Activations Density 0.002%

    No Known Activations