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. 84559
    Prev
    Next
    INDEX
    Explanations

    text

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of the “message” or “text” fields that specify what will be printed or echoed to the console.

    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
    .Host
    -0.07
     hk
    -0.06
    .RESET
    -0.06
    future
    -0.06
    (package
    -0.06
    ////////////
    -0.06
    @synthesize
    -0.06
    ($"{
    -0.06
    =zeros
    -0.06
    /******************************************************************************↵
    -0.06
    POSITIVE LOGITS
     mall
    0.06
    γράφ
    0.06
     constructive
    0.06
    ूब
    0.06
     Async
    0.06
    B
    0.06
    rub
    0.06
    ges
    0.06
     JButton
    0.06
     Crowd
    0.06
    Activations Density 0.038%

    No Known Activations