© 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. 102043
    Prev
    Next
    INDEX
    Explanations

    x

    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
     Positive
    -0.07
     Fraction
    -0.07
    .HTML
    -0.07
     Offline
    -0.06
    "Yeah
    -0.06
    wchar
    -0.06
    	Array
    -0.06
     Salem
    -0.06
    alim
    -0.06
     природ
    -0.06
    POSITIVE LOGITS
     đọ
    0.06
     خویش
    0.06
     reused
    0.06
    ící
    0.06
    ssql
    0.06
     glUniform
    0.06
     actress
    0.06
    does
    0.06
    (be
    0.06
     does
    0.06
    Activations Density 0.012%

    No Known Activations