© 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. 7-RESID-POST-AA
    11. 115862
    Prev
    Next
    INDEX
    Explanations

    ably

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     솔
    -0.07
     yol
    -0.07
     пласти
    -0.06
     lasting
    -0.06
     вой
    -0.06
    elerle
    -0.06
     digestion
    -0.06
     답변
    -0.06
     jacket
    -0.06
     budou
    -0.06
    POSITIVE LOGITS
     interchangeable
    0.10
     interchange
    0.09
    CallBack
    0.07
     spaces
    0.06
     ph
    0.06
     ur
    0.06
    loh
    0.06
     __________________________________
    0.06
     Or
    0.06
    ्वच
    0.06
    Activations Density 0.002%

    No Known Activations