© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 56331
    Prev
    Next
    INDEX
    Explanations

    charisma

    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
    \Exception
    -0.07
    。",↵
    -0.06
     possessing
    -0.06
     ldap
    -0.06
    datap
    -0.06
     effortless
    -0.06
     Marshal
    -0.06
    /key
    -0.06
    Piece
    -0.06
     داشتند
    -0.06
    POSITIVE LOGITS
     ovšem
    0.07
    ुरक
    0.07
    ième
    0.07
     Cyan
    0.07
    Ù
    0.06
     نگهد
    0.06
    -confidence
    0.06
    angible
    0.06
    ARGIN
    0.06
    altet
    0.06
    Activations Density 0.264%

    No Known Activations