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. 130293
    Prev
    Next
    INDEX
    Explanations

    Code class structures

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric tokens representing floating‐point or decimal numbers (e.g., “0.327392578125,” “1.9033203125,” etc.).

    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
     Opt
    -0.07
     VERSION
    -0.07
     professionalism
    -0.06
     Vice
    -0.06
     wording
    -0.06
    ,\"
    -0.06
    .V
    -0.06
     flavours
    -0.06
     yazar
    -0.06
     mathematics
    -0.06
    POSITIVE LOGITS
     moh
    0.07
     růz
    0.06
     yönelik
    0.06
     trú
    0.06
    emony
    0.06
     různ
    0.06
     rok
    0.06
     здійснення
    0.06
     підтрим
    0.06
     Autodesk
    0.06
    Activations Density 0.006%

    No Known Activations