© 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. 45151
    Prev
    Next
    INDEX
    Explanations

    personal stories

    np_max-act · gemini-2.0-flash

    references to personal relationships and emotional complexity.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    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
    yh
    -0.07
     были
    -0.07
    ัวเอง
    -0.07
     milionů
    -0.07
     相
    -0.06
    FileInfo
    -0.06
     olmaktadır
    -0.06
    ضوع
    -0.06
    τικό
    -0.06
    لق
    -0.06
    POSITIVE LOGITS
     Chicago
    0.06
    gd
    0.06
    orp
    0.06
    Cols
    0.06
    μι
    0.06
     ван
    0.06
     Jersey
    0.06
    bolt
    0.06
    HomeController
    0.05
    -aged
    0.05
    Activations Density 0.017%

    No Known Activations