© 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. 91081
    Prev
    Next
    INDEX
    Explanations

    n

    np_max-act · gemini-2.0-flash

    This neuron primarily activates on the occurrences of the parameter “n” (and related numeric parameters) inside mathematical group names or formulas (e.g. in “SL(n,ℤ)” and similar expressions).

    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
    Blue
    -0.07
    _kill
    -0.07
     عالية
    -0.07
    White
    -0.06
    agina
    -0.06
    umped
    -0.06
     Arc
    -0.06
     webView
    -0.06
     Quiz
    -0.06
    лин
    -0.06
    POSITIVE LOGITS
     reviewer
    0.07
     sidew
    0.07
     nak
    0.06
     меди
    0.06
     الاح
    0.06
     Mumbai
    0.06
    charging
    0.06
     πρω
    0.06
     packing
    0.06
    Computed
    0.06
    Activations Density 0.003%

    No Known Activations