© 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. 110573
    Prev
    Next
    INDEX
    Explanations

    use

    np_max-act · gemini-2.0-flash

    This neuron detects verbs in legal or real-estate contexts that describe granting or using rights (e.g. “to use,” “to occupy,” “to access”).

    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
    Offers
    -0.06
     Gecko
    -0.06
    ose
    -0.06
    =zeros
    -0.06
    -Jul
    -0.06
     deviation
    -0.06
     Abel
    -0.06
     десят
    -0.06
     TRACE
    -0.06
    DE
    -0.06
    POSITIVE LOGITS
     UserManager
    0.07
     dedi
    0.07
    Rib
    0.06
    实在
    0.06
    ebb
    0.06
    �
    0.06
     urg
    0.06
     Entered
    0.06
    preh
    0.06
     пользоват
    0.06
    Activations Density 0.023%

    No Known Activations