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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 40410
    Prev
    Next
    INDEX
    Explanations

    Science and mathematics

    np_max-act · gemini-2.0-flash

    The neuron activates on phrases describing an integral as the “area under a curve” or the “sum of infinitely many small quantities.”

    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
     messenger
    -0.07
     derivative
    -0.06
    计划
    -0.06
     VAR
    -0.06
    ev
    -0.06
     Nas
    -0.06
    _pre
    -0.06
    sec
    -0.06
     cof
    -0.06
     Goodman
    -0.06
    POSITIVE LOGITS
    [word
    0.06
     생각
    0.06
    batis
    0.06
    巨
    0.06
    <!--<
    0.06
    Rib
    0.06
    (Conv
    0.06
    .Element
    0.06
    оратив
    0.06
     _("
    0.06
    Activations Density 0.038%

    No Known Activations