© 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. 58155
    Prev
    Next
    INDEX
    Explanations

    Formulas/Symbols

    np_max-act · gemini-2.0-flash

    The neuron activates on short pollutant codes or abbreviations (e.g. “NO,” “PM_10,” “PM_2.5”) in scientific text.

    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
    ]?.
    -0.06
    #plt
    -0.06
     container
    -0.06
    consider
    -0.06
    .hpp
    -0.06
     simple
    -0.06
    landır
    -0.06
    .toBe
    -0.05
    InitStruct
    -0.05
     blend
    -0.05
    POSITIVE LOGITS
    <Entry
    0.07
     ostream
    0.07
    кий
    0.07
    чки
    0.06
     nesta
    0.06
    Delegate
    0.06
     Martial
    0.06
     друж
    0.06
     vede
    0.06
    _RAW
    0.06
    Activations Density 0.212%

    No Known Activations