© 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. 27-RESID-POST-AA
    11. 93430
    Prev
    Next
    INDEX
    Explanations

    Code/Programming

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     yaygın
    -0.07
     Vintage
    -0.07
    odal
    -0.07
     vintage
    -0.06
    สต
    -0.06
    _started
    -0.06
    -employed
    -0.06
     older
    -0.06
    เวอร
    -0.06
     Pediatrics
    -0.06
    POSITIVE LOGITS
    組織
    0.07
    atri
    0.06
     Mỹ
    0.06
    Cooldown
    0.06
     Charity
    0.06
    軟
    0.06
     रख
    0.06
    ibi
    0.06
     Trying
    0.06
     hon
    0.06
    Activations Density 0.018%

    No Known Activations