© 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 EvalsExportsAPI 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. 103522
    Prev
    Next
    INDEX
    Explanations

    the

    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
     merger
    -0.07
     amb
    -0.07
     Fond
    -0.07
     esl
    -0.07
     fraud
    -0.06
     fond
    -0.06
    oru
    -0.06
     συ
    -0.06
    spread
    -0.06
    VRT
    -0.06
    POSITIVE LOGITS
    }-
    0.07
    Ideal
    0.07
    }elseif
    0.07
    }")↵
    0.07
    */
↵
    0.06
    ()]↵
    0.06
    İK
    0.06
     DataService
    0.06
    .setId
    0.06
    .Patient
    0.06
    Activations Density 0.030%

    No Known Activations