© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 127146
    Prev
    Next
    INDEX
    Explanations

    Punctuation/stop words

    np_max-act · gemini-2.0-flash

    This neuron responds to technical language describing physiological or pathological mechanisms (e.g. terms like “reduction,” “absorption,” “inflammation,” “chronic,” “through,” “contribute,” “loss”).

    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
     tents
    -0.07
     XB
    -0.07
    fections
    -0.06
     Parks
    -0.06
    。那
    -0.06
     share
    -0.06
    _age
    -0.06
    .Function
    -0.06
    лід
    -0.06
     ARR
    -0.06
    POSITIVE LOGITS
    'nun
    0.07
    std
    0.06
    onnement
    0.06
     нужно
    0.06
    jed
    0.06
     Porno
    0.06
    _blk
    0.06
    зд
    0.06
     chảy
    0.06
    stdexcept
    0.06
    Activations Density 0.089%

    No Known Activations