© 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. 7-RESID-POST-AA
    11. 92051
    Prev
    Next
    INDEX
    Explanations

    validates

    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
     weight
    -0.07
     volcan
    -0.07
     pars
    -0.06
     defendants
    -0.06
    .gener
    -0.06
     overl
    -0.06
    COL
    -0.06
    extern
    -0.06
     outbound
    -0.06
    也是
    -0.06
    POSITIVE LOGITS
    тив
    0.07
    <TResult
    0.06
     uw
    0.06
    pro
    0.06
     aup
    0.06
    /off
    0.06
    CLUD
    0.06
     Mühendis
    0.06
     Confidential
    0.06
    ienne
    0.05
    Activations Density 0.005%

    No Known Activations