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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 44969
    Prev
    Next
    INDEX
    Explanations

    part

    np_max-act · gemini-2.0-flash

    The neuron fires on legal code citations, especially when introducing quoted statutes or regulations with lead-in phrases like “in pertinent part.”

    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
     Form
    -0.06
     directly
    -0.06
    ceptors
    -0.06
     Quest
    -0.06
    ocket
    -0.06
     Mitarbeiter
    -0.06
     voksne
    -0.06
     bur
    -0.06
    Custom
    -0.06
    =val
    -0.06
    POSITIVE LOGITS
     Conversely
    0.06
     Kathryn
    0.06
    _KEYS
    0.06
    301
    0.06
    ActionCode
    0.06
     khoảng
    0.06
     allowNull
    0.06
     nerve
    0.06
    花
    0.06
     хорошо
    0.06
    Activations Density 0.002%

    No Known Activations