© 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. 126782
    Prev
    Next
    INDEX
    Explanations

    gemstones

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of gemstones (e.g., sapphire, gem, gemstone).

    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
    _NODES
    -0.07
     satu
    -0.07
    (min
    -0.07
     Station
    -0.06
     Faker
    -0.06
     lcd
    -0.06
    bjerg
    -0.06
     wind
    -0.06
     Bride
    -0.06
    疾
    -0.06
    POSITIVE LOGITS
     Sapphire
    0.08
    apphire
    0.07
    AGON
    0.07
     opaque
    0.06
    ып
    0.06
    LOS
    0.06
     shattered
    0.06
    できます
    0.06
    лав
    0.06
    ubber
    0.06
    Activations Density 0.011%

    No Known Activations