© 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. 11-RESID-POST-AA
    11. 58126
    Prev
    Next
    INDEX
    Explanations

    holders

    np_max-act · gemini-2.0-flash

    The neuron fires on the word “holders” (as in “copyright holders”) in software license and copyright notice blocks.

    oai_token-act-pair · o4-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
     Afterwards
    -0.07
    _dependency
    -0.06
     Địa
    -0.06
    .Shared
    -0.06
     сколько
    -0.06
     <<<
    -0.06
     Xbox
    -0.06
     compil
    -0.06
     ống
    -0.06
    Repeated
    -0.06
    POSITIVE LOGITS
    حث
    0.07
    _href
    0.07
     změn
    0.07
    period
    0.07
     overdue
    0.06
    σαν
    0.06
     ifdef
    0.06
     balancing
    0.06
    yii
    0.06
    める
    0.06
    Activations Density 0.002%

    No Known Activations