© 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. 127469
    Prev
    Next
    INDEX
    Explanations

    physical

    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
     minden
    -0.08
     declining
    -0.07
     interfere
    -0.07
     err
    -0.07
     Coming
    -0.07
     gn
    -0.07
     mend
    -0.07
     tuples
    -0.07
     January
    -0.07
     prolonged
    -0.07
    POSITIVE LOGITS
     İngiliz
    0.09
    물
    0.08
    形
    0.08
     physical
    0.08
    phy
    0.08
     fís
    0.08
     Physics
    0.08
     плот
    0.08
    imple
    0.08
     kích
    0.08
    Activations Density 0.032%

    No Known Activations