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. 130437
    Prev
    Next
    INDEX
    Explanations

    metallic

    np_max-act · gemini-2.0-flash

    This neuron activates on floating-point numeric literals (decimal 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
     saúde
    -0.08
     установки
    -0.06
     ایجاد
    -0.06
     KNOW
    -0.06
    _rates
    -0.06
     завдання
    -0.06
    avis
    -0.06
    Retrieve
    -0.06
    адження
    -0.06
    “There
    -0.06
    POSITIVE LOGITS
     metallic
    0.10
     Metallic
    0.08
     nhựa
    0.07
    lic
    0.07
    ported
    0.07
    %),
    0.06
    ');?></
    0.06
    .onPause
    0.06
    唯
    0.06
     ""
    ↵
    0.06
    Activations Density 0.003%

    No Known Activations