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. 130608
    Prev
    Next
    INDEX
    Explanations

    dash

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens (numbers, especially decimals) in code or data.

    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
     άν
    -0.06
     منظ
    -0.06
     coolant
    -0.06
    ']],
    -0.06
     단
    -0.06
     guiActive
    -0.06
     потер
    -0.06
    .keyCode
    -0.06
     HTC
    -0.06
    .:.:.:.:.:.:.:.:.:.:.:.:.:.:.:.:
    -0.06
    POSITIVE LOGITS
     Scene
    0.07
     Areas
    0.07
    管理员
    0.07
    .assertNot
    0.07
     arasındaki
    0.06
    ець
    0.06
     faker
    0.06
    soup
    0.06
    _TRANSFORM
    0.06
     хозя
    0.06
    Activations Density 0.003%

    No Known Activations