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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 84603
    Prev
    Next
    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    This neuron activates primarily on numeric tokens, detecting the presence of numbers in the text.

    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
     DLC
    -0.07
    itsu
    -0.06
    veau
    -0.06
     Apprentice
    -0.06
     Duy
    -0.06
    _evaluation
    -0.06
     decentral
    -0.06
    .combine
    -0.06
    sections
    -0.06
    calculate
    -0.06
    POSITIVE LOGITS
     weekly
    0.08
    ZN
    0.07
     crem
    0.06
    .channel
    0.06
     مث
    0.06
    -area
    0.06
    ąd
    0.06
     intended
    0.06
     espaço
    0.06
     aiding
    0.06
    Activations Density 0.010%

    No Known Activations