© 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. 59276
    Prev
    Next
    INDEX
    Explanations

    Equations/Formulas

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the symbol “n” (and similar index variables) in mathematical expressions, especially as a subscript or in parentheses.

    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
     securely
    -0.07
    енную
    -0.07
     jó
    -0.06
    contrast
    -0.06
    57
    -0.06
    _dependency
    -0.06
    +'
    -0.06
     Qed
    -0.06
     Meredith
    -0.06
    _DEC
    -0.06
    POSITIVE LOGITS
    .country
    0.06
     vẫn
    0.06
    elocity
    0.06
     pohy
    0.06
     igen
    0.06
     thăm
    0.06
     Demand
    0.06
     cover
    0.06
     FString
    0.06
    rgba
    0.06
    Activations Density 0.040%

    No Known Activations