© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 30210
    Prev
    Next
    INDEX
    Explanations

    moi

    np_max-act · gemini-2.0-flash

    The neuron fires on terms referring to molecular substructures—e.g. “moiety,” “skeleton,” or “functionalities.”

    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
    responseData
    -0.07
    ocused
    -0.07
     puts
    -0.07
    TER
    -0.06
     invaluable
    -0.06
    ysql
    -0.06
     banks
    -0.06
    tings
    -0.06
     bank
    -0.06
    дать
    -0.06
    POSITIVE LOGITS
     motif
    0.09
     moi
    0.08
     motifs
    0.08
     kod
    0.06
    lev
    0.06
     відмов
    0.06
     emoji
    0.06
    maj
    0.06
    getHeight
    0.06
     statutes
    0.06
    Activations Density 0.003%

    No Known Activations