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. 86160
    Prev
    Next
    INDEX
    Explanations

    >Main

    np_max-act · gemini-2.0-flash

    The neuron fires on the top‐level navigation tab labels (e.g. “Main Page,” “Modules,” “Files,” “Classes”) in a Doxygen‐generated HTML header.

    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
    (bucket
    -0.07
    (saved
    -0.07
    /layouts
    -0.07
    ,因为
    -0.06
     вода
    -0.06
     العل
    -0.06
    _SIZE
    -0.06
     виник
    -0.06
    azel
    -0.06
    isu
    -0.06
    POSITIVE LOGITS
     :,
    0.06
    >Main
    0.06
    .undefined
    0.06
    .Create
    0.06
    包含
    0.06
    .Support
    0.06
    sad
    0.06
     phê
    0.06
    Up
    0.06
    _PROFILE
    0.06
    Activations Density 0.000%

    No Known Activations