© 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. 57576
    Prev
    Next
    INDEX
    Explanations

    Scientific studies

    np_max-act · gemini-2.0-flash

    The neuron responds to numeric tokens that include decimal points (i.e. floating‐point numbers).

    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
     slightest
    -0.07
     BİL
    -0.06
     به
    -0.06
    _OF
    -0.06
     tuy
    -0.06
    -gl
    -0.06
     ballo
    -0.06
     unbe
    -0.06
     newSize
    -0.06
    Ionic
    -0.06
    POSITIVE LOGITS
     культуры
    0.07
    ै,
    0.07
    Dashboard
    0.07
     Au
    0.06
    월
    0.06
    -invalid
    0.06
     прим
    0.06
    cash
    0.06
    _payment
    0.06
    Employee
    0.06
    Activations Density 0.172%

    No Known Activations