© 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. 7-RESID-POST-AA
    11. 34927
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    function words, especially the definite article signaling the start of a noun phrase

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
     پیک
    -0.06
    getCode
    -0.06
     умень
    -0.05
     PLATFORM
    -0.05
     nighttime
    -0.05
     Minimal
    -0.05
    (rotation
    -0.05
     Execution
    -0.05
    рут
    -0.05
     TL
    -0.05
    POSITIVE LOGITS
    mer
    0.07
    oad
    0.07
    тож
    0.07
    .Ο
    0.06
    "=>"
    0.06
    ığ
    0.06
    .Click
    0.06
    _SURFACE
    0.06
     olumlu
    0.06
    لاین
    0.06
    Activations Density 0.271%

    No Known Activations