© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 36237
    Prev
    Next
    INDEX
    Explanations

    in

    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
     NVIC
    -0.06
    мест
    -0.06
    руч
    -0.06
     vegetation
    -0.06
     гро
    -0.06
    谋
    -0.06
     пись
    -0.06
     Jacobs
    -0.06
    Cancel
    -0.06
     Seth
    -0.06
    POSITIVE LOGITS
     الأمريكية
    0.07
    ':
    0.06
     origen
    0.06
    .ON
    0.06
    BUFF
    0.06
     rebuilt
    0.06
     IPV
    0.06
    μό
    0.06
    _Adjust
    0.06
    .Α
    0.06
    Activations Density 0.044%

    No Known Activations