© 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. 58859
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    This neuron responds to code tokens that are object-member accesses or method calls (i.e. the “object.method” or “object.property” patterns).

    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
    variants
    -0.06
    stellen
    -0.06
    PARSE
    -0.06
    КИ
    -0.06
    slack
    -0.06
     Evropy
    -0.06
     ebay
    -0.06
     необхідно
    -0.06
    lord
    -0.06
    伍
    -0.06
    POSITIVE LOGITS
    .Number
    0.07
     intoler
    0.06
     interceptor
    0.06
     จาก
    0.06
     retal
    0.06
     темп
    0.06
    uty
    0.06
    overe
    0.06
     عملیات
    0.06
     mínimo
    0.06
    Activations Density 0.135%

    No Known Activations