© 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. 15-RESID-POST-AA
    11. 24181
    Prev
    Next
    INDEX
    Explanations

    §

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Blockchain
    -0.07
    _EXPECT
    -0.06
    งช
    -0.06
     الخاصة
    -0.06
    _AP
    -0.06
     dette
    -0.06
    handle
    -0.06
    리가
    -0.06
    navbarSupportedContent
    -0.06
    .characters
    -0.06
    POSITIVE LOGITS
     sesame
    0.08
    (-
    0.07
     ew
    0.07
    .labels
    0.06
     honeymoon
    0.06
     filenames
    0.06
    .final
    0.06
    MetaData
    0.06
     wake
    0.06
     Sloven
    0.06
    Activations Density 0.000%

    No Known Activations