© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 110099
    Prev
    Next
    INDEX
    Explanations

    Technical/Code related

    np_max-act · gemini-2.0-flash

    The neuron activates specifically on floating‐point numeric literals (i.e. decimal 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
    .getRow
    -0.07
    Bounds
    -0.07
     chrome
    -0.07
    unprocessable
    -0.06
    ased
    -0.06
     zprávy
    -0.06
    bě
    -0.06
     fingers
    -0.06
    uable
    -0.06
     reporters
    -0.06
    POSITIVE LOGITS
     демон
    0.07
     StreamLazy
    0.07
     Cos
    0.07
     trí
    0.06
    ?>">↵
    0.06
     op
    0.06
    ціон
    0.06
    (st
    0.06
    ucs
    0.06
     svého
    0.06
    Activations Density 0.000%

    No Known Activations