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. 130320
    Prev
    Next
    INDEX
    Explanations

    Game settings/code

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on decimal number literals (floating-point values).

    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
     kne
    -0.08
    ature
    -0.08
    _Date
    -0.07
     (...
    -0.07
     Lazar
    -0.07
    :M
    -0.07
     Coronavirus
    -0.07
    SA
    -0.06
     phrase
    -0.06
    lymp
    -0.06
    POSITIVE LOGITS
    ична
    0.06
    有点
    0.06
    しよう
    0.06
     '''
    ↵
    0.06
    Susan
    0.06
    }`);↵↵
    0.06
     bueno
    0.06
     字
    0.05
     Yeni
    0.05
     hodně
    0.05
    Activations Density 0.018%

    No Known Activations