© 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. 91331
    Prev
    Next
    INDEX
    Explanations

    Arg or context

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of optional callback context parameters (e.g. “context” or “thisArg”) used when calling or binding functions.

    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
    っても
    -0.06
     covers
    -0.06
    [temp
    -0.06
     membership
    -0.06
    ğında
    -0.06
     analytics
    -0.06
    .neighbors
    -0.06
    umont
    -0.06
    session
    -0.06
     heuristic
    -0.06
    POSITIVE LOGITS
     پاس
    0.06
     součást
    0.06
     Vacuum
    0.06
     Parm
    0.06
     immobil
    0.06
    Wallet
    0.06
     adjective
    0.06
     Bond
    0.06
    ابعة
    0.06
     راه
    0.06
    Activations Density 0.003%

    No Known Activations