© 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. 19-RESID-POST-AA
    11. 109869
    Prev
    Next
    INDEX
    Explanations

    stack

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     muted
    -0.07
    ेहतर
    -0.07
     Manor
    -0.06
     breeds
    -0.06
    avanaugh
    -0.06
     Lans
    -0.06
     Thornton
    -0.06
     giorni
    -0.06
     '{}'
    -0.06
     "',
    -0.06
    POSITIVE LOGITS
    蒂
    0.07
     अगल
    0.07
     incom
    0.07
    IC
    0.07
    .tip
    0.07
    γραφ
    0.06
    adier
    0.06
    /am
    0.06
    Touch
    0.06
     hend
    0.06
    Activations Density 0.003%

    No Known Activations