© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 6884
    Prev
    Next
    INDEX
    Explanations

    methods and functions

    np_max-act · gemini-2.0-flash

    The neuron fires on the declaration of the program’s main function (e.g. the “main()” signature and related keywords).

    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
     taxing
    -0.06
     prophet
    -0.06
     Herman
    -0.06
    vä
    -0.06
    stored
    -0.06
     argued
    -0.06
     تحصیل
    -0.06
     pudding
    -0.06
     IMapper
    -0.06
     CIA
    -0.05
    POSITIVE LOGITS
     шляхом
    0.07
    /delete
    0.07
    @WebServlet
    0.06
     تجه
    0.06
    之后
    0.06
    GNUC
    0.06
    _producto
    0.06
    .channels
    0.06
    (nr
    0.06
     کتاب
    0.06
    Activations Density 0.046%

    No Known Activations