© 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. 11-RESID-POST-AA
    11. 46508
    Prev
    Next
    INDEX
    Explanations

    Questions and answers

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]],↵
    -0.07
    ringe
    -0.07
    iration
    -0.06
     materials
    -0.06
    igm
    -0.06
    session
    -0.06
     flushing
    -0.06
     wearer
    -0.06
    circle
    -0.06
     detention
    -0.06
    POSITIVE LOGITS
    ابقه
    0.07
    -ac
    0.07
    -ap
    0.06
    лаж
    0.06
    氧
    0.06
    .getMax
    0.06
    .GetAll
    0.06
    _idx
    0.06
     Costa
    0.06
    .Append
    0.06
    Activations Density 0.000%

    No Known Activations