© 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. 23-RESID-POST-AA
    11. 8213
    Prev
    Next
    INDEX
    Explanations

    image hosting URLs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Blob
    -0.06
    ’T
    -0.06
    Room
    -0.06
    _Clear
    -0.06
    ไปย
    -0.06
     flea
    -0.06
    cab
    -0.06
    (usuario
    -0.06
    ehicles
    -0.06
     Tops
    -0.05
    POSITIVE LOGITS
    /autoload
    0.07
    logic
    0.07
    -circle
    0.07
    ická
    0.07
     postfix
    0.06
    awi
    0.06
     Holocaust
    0.06
    ่อย
    0.06
    .invoke
    0.06
     Echo
    0.06
    Activations Density 0.022%

    No Known Activations