© 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. 44107
    Prev
    Next
    INDEX
    Explanations

    memorandum

    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
     drive
    -0.07
    Brains
    -0.07
     Legs
    -0.06
    itial
    -0.06
    q
    -0.06
     fait
    -0.06
    plates
    -0.06
    敌
    -0.06
    .angular
    -0.06
    صة
    -0.06
    POSITIVE LOGITS
     memorandum
    0.11
     Memor
    0.09
    Memo
    0.08
     Igor
    0.07
     Note
    0.07
     memor
    0.06
     wore
    0.06
    Mem
    0.06
    Cream
    0.06
    Refer
    0.06
    Activations Density 0.005%

    No Known Activations