© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 59451
    Prev
    Next
    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash

    The neuron fires on the “acknowledgement” portion of BSD‐style license headers—i.e. the numbered/bulleted clause that begins “the following acknowledgement:” or “This product includes software developed by…”

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     dearly
    -0.07
    wishlist
    -0.07
    ?>"></
    -0.06
    混
    -0.06
    scene
    -0.06
    ноп
    -0.06
    _help
    -0.06
    	scene
    -0.06
     nid
    -0.06
     guru
    -0.06
    POSITIVE LOGITS
    Consulta
    0.06
    amodel
    0.06
    Subscription
    0.06
    ète
    0.06
     assessing
    0.06
    .complete
    0.06
     Obamacare
    0.06
     ---------------------------------------------------------------------------↵
    0.06
    Compute
    0.06
    Commercial
    0.06
    Activations Density 0.004%

    No Known Activations