© 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. 7-RESID-POST-AA
    11. 92868
    Prev
    Next
    INDEX
    Explanations

    buns

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (clean
    -0.07
     FEC
    -0.06
    icht
    -0.06
    OTH
    -0.06
    ODEV
    -0.06
     グ
    -0.06
     vhod
    -0.06
     손을
    -0.06
    χεδόν
    -0.06
     Kuzey
    -0.06
    POSITIVE LOGITS
     bun
    0.13
     Bun
    0.11
    utut
    0.08
     rolls
    0.07
     obtaining
    0.07
    ॉन
    0.07
     bud
    0.07
     ·
    0.07
    latest
    0.07
     reducing
    0.07
    Activations Density 0.001%

    No Known Activations