© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 27-RESID-POST-AA
    11. 35950
    Prev
    Next
    INDEX
    Explanations

    casinos and gambling

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sharedInstance
    -0.06
    olicies
    -0.06
    「そう
    -0.06
     swift
    -0.06
    Debugger
    -0.06
     servers
    -0.06
    _handling
    -0.06
     packet
    -0.06
     callbacks
    -0.06
    ythe
    -0.06
    POSITIVE LOGITS
     jr
    0.07
     onların
    0.07
    urv
    0.07
     اینترنتی
    0.07
    Summon
    0.06
     =========================================================================
    0.06
     출
    0.06
     Oyun
    0.06
     우
    0.06
     intolerance
    0.06
    Activations Density 0.012%

    No Known Activations