© 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. 57979
    Prev
    Next
    INDEX
    Explanations

    start

    np_max-act · gemini-2.0-flash

    This neuron activates on variable or field names that denote the start or end of a range (e.g. “start,” “end,” “row_start,” “col_start”).

    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
    fixed
    -0.07
    Asia
    -0.06
    _DELAY
    -0.06
    敦
    -0.06
    ération
    -0.06
     postId
    -0.06
     competitor
    -0.06
    INARY
    -0.06
    Forecast
    -0.06
     anlamda
    -0.06
    POSITIVE LOGITS
     Vlad
    0.07
    시는
    0.07
     threadIdx
    0.07
     Muse
    0.07
     essentials
    0.06
     *}
    0.06
    NotBlank
    0.06
     самов
    0.06
    kon
    0.06
     تف
    0.06
    Activations Density 0.030%

    No Known Activations