© 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. 23-RESID-POST-AA
    11. 64469
    Prev
    Next
    INDEX
    Explanations

    Comparisons

    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /bin
    -0.06
     convert
    -0.06
     нам
    -0.06
     населення
    -0.06
    yahoo
    -0.06
    _keys
    -0.06
     wildlife
    -0.06
     Streams
    -0.06
    _Null
    -0.06
     gamma
    -0.06
    POSITIVE LOGITS
    InTheDocument
    0.07
    (['/
    0.06
    нич
    0.06
    481
    0.06
     Sage
    0.06
    rollment
    0.06
    경기
    0.06
    >');
    0.06
    Vis
    0.06
    688
    0.06
    Activations Density 0.183%

    No Known Activations