Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 93040
    Prev
    Next
    INDEX
    Explanations

    /

    np_max-act · gemini-2.0-flash

    The neuron is primarily activated by numeric tokens representing floating-point values (numbers with decimal points).

    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
    948
    -0.06
     всю
    -0.06
     entirely
    -0.06
     Favorites
    -0.06
     teas
    -0.06
    _Frame
    -0.06
     themselves
    -0.06
     putchar
    -0.05
     Dup
    -0.05
    _ranges
    -0.05
    POSITIVE LOGITS
    /
    0.08
    وبی
    0.07
    أن
    0.07
    ी-
    0.07
    ?#
    0.07
    ากาศ
    0.07
    ी
    0.06
    :
    0.06
     biç
    0.06
    companyId
    0.06
    Activations Density 0.008%

    No Known Activations