© 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. 24215
    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
     Highlands
    -0.07
     guid
    -0.07
     Fare
    -0.06
     Gazette
    -0.06
     Rede
    -0.06
     Gould
    -0.06
    stile
    -0.06
    pants
    -0.06
    оян
    -0.06
     welt
    -0.06
    POSITIVE LOGITS
     sayf
    0.07
    (java
    0.06
    (sl
    0.06
     xbmc
    0.06
    CL
    0.06
     Baylor
    0.06
     plag
    0.06
     新
    0.06
     packages
    0.06
    他們
    0.06
    Activations Density 0.000%

    No Known Activations