© 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
    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. 91666
    Prev
    Next
    INDEX
    Explanations

    election

    np_max-act · gemini-2.0-flash

    The neuron activates on words naming or describing elections and their types (e.g. “election,” “gubernatorial,” “presidential,” “primary”).

    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
    fadeIn
    -0.07
     nhất
    -0.07
     Wealth
    -0.07
    pheres
    -0.06
    __()
    -0.06
     hoàn
    -0.06
     мира
    -0.06
     Tanks
    -0.06
     Coral
    -0.06
     Bend
    -0.06
    POSITIVE LOGITS
     веществ
    0.07
     sealed
    0.07
    icrosoft
    0.07
     dall
    0.07
     Đ
    0.07
     detailed
    0.06
     또
    0.06
     unfit
    0.06
    stored
    0.06
     rumored
    0.06
    Activations Density 0.006%

    No Known Activations