© 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. 25051
    Prev
    Next
    INDEX
    Explanations

    point

    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
     nickel
    -0.07
    냐
    -0.07
    \Notifications
    -0.06
    callable
    -0.06
     Kraft
    -0.06
     scripted
    -0.06
     tobacco
    -0.06
    ращения
    -0.06
     Kick
    -0.06
    =post
    -0.06
    POSITIVE LOGITS
     top
    0.07
    Binding
    0.07
     gro
    0.06
    /xhtml
    0.06
     fotos
    0.06
     cứu
    0.06
    خصص
    0.06
     exhausting
    0.06
     dět
    0.06
     prova
    0.06
    Activations Density 0.142%

    No Known Activations