© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 30031
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas

    np_max-act · gemini-2.0-flash

    The neuron fires on LaTeX‐style mathematical notation—e.g. dollar signs, backslashes and math commands—i.e. it detects when the text is a math expression.

    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
    _objects
    -0.07
    ì
    -0.07
     duct
    -0.07
    micro
    -0.07
    Disconnected
    -0.06
    .drawText
    -0.06
    Aura
    -0.06
     RSS
    -0.06
     ^^
    -0.06
    _calls
    -0.06
    POSITIVE LOGITS
     "[
    0.06
     #'
    0.06
     RTC
    0.06
    므로
    0.06
    ARDS
    0.06
     ASS
    0.06
     tariffs
    0.05
     употреб
    0.05
     "<
    0.05
     měsíců
    0.05
    Activations Density 0.003%

    No Known Activations