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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 68613
    Prev
    Next
    INDEX
    Explanations

    Business names/abbreviations

    np_max-act · gemini-2.0-flash

    This neuron detects CamelCase or alphanumeric compound tokens—i.e. brand, product, or model names (e.g. PacketZoom, LCZ696, NobelDirect, Glasspar).

    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
    WXYZ
    -0.07
    ablo
    -0.07
    TU
    -0.07
    Mine
    -0.07
     sahip
    -0.06
     ули
    -0.06
    ैन
    -0.06
     passphrase
    -0.06
    yclic
    -0.06
    Flex
    -0.06
    POSITIVE LOGITS
    /weather
    0.07
     (...
    0.06
     дых
    0.06
     ()
↵
    0.06
     flight
    0.06
    (pow
    0.06
     allergy
    0.06
    .elements
    0.06
    .output
    0.06
     marginal
    0.06
    Activations Density 0.156%

    No Known Activations