© 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. 23-RESID-POST-AA
    6. 8230
    Prev
    Next
    INDEX
    Explanations

    command

    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
    roph
    -0.07
     unidentified
    -0.07
    _nonce
    -0.06
    .scal
    -0.06
    _picker
    -0.06
     До
    -0.06
    iciente
    -0.06
    層
    -0.06
    ائر
    -0.06
     Я
    -0.06
    POSITIVE LOGITS
     कहत
    0.08
     command
    0.07
     Command
    0.07
     accommodation
    0.07
     extracting
    0.07
     Precision
    0.07
     Should
    0.07
     Inform
    0.07
     ویژ
    0.06
     Tart
    0.06
    Activations Density 0.009%

    No Known Activations