© 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. 83246
    Prev
    Next
    INDEX
    Explanations

    1

    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
     shocking
    -0.06
     raw
    -0.06
    .quality
    -0.06
     hal
    -0.06
     turbulent
    -0.06
    (trigger
    -0.06
    ขณะ
    -0.06
    andi
    -0.06
     derivative
    -0.06
    God
    -0.06
    POSITIVE LOGITS
     Physiology
    0.06
    /Core
    0.06
    $smarty
    0.06
     civilized
    0.06
    (Application
    0.06
    ;?>
    0.06
    --↵
    0.06
     vict
    0.06
    <<"\
    0.06
    _POSITION
    0.06
    Activations Density 0.003%

    No Known Activations