Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 126417
    Prev
    Next
    INDEX
    Explanations

    computer programs and scripts

    np_max-act · gemini-2.0-flash

    The neuron activates on references to the software system under discussion—words naming the program or service (e.g. “service,” “program,” “job,” or specific application names).

    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
     ट
    -0.07
    example
    -0.07
     Rahul
    -0.06
     bal
    -0.06
    .study
    -0.06
     blown
    -0.06
    sword
    -0.06
     organize
    -0.06
     traders
    -0.06
    .getResult
    -0.06
    POSITIVE LOGITS
     intrusive
    0.07
    omnia
    0.06
     royalties
    0.06
    Equip
    0.06
    _NV
    0.06
     Nicolas
    0.06
    (cuda
    0.06
    .Children
    0.06
    、
    0.06
     Cyprus
    0.06
    Activations Density 0.135%

    No Known Activations