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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 12816
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron activates on Vim‐script syntax‐highlighting directives (e.g. “syn keyword,” “syn match,” “syn region”).

    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
    [E
    -0.07
    INDEX
    -0.06
     stderr
    -0.06
     Domin
    -0.06
    ISM
    -0.06
    است
    -0.06
     Bout
    -0.06
     tím
    -0.06
    자의
    -0.06
    ưu
    -0.06
    POSITIVE LOGITS
     cruising
    0.06
    妈
    0.06
     troll
    0.06
    =plt
    0.06
    ほ
    0.06
     achieved
    0.06
     barcelona
    0.06
     ülk
    0.06
    EventManager
    0.06
    Outlet
    0.06
    Activations Density 0.047%

    No Known Activations