© 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. 43000
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of material or chemical property descriptors (e.g., activity, behavior, character, hydrophilicity, amphiphilicity, polar nature).

    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
     كر
    -0.06
     sorter
    -0.06
     scams
    -0.06
     크
    -0.06
     MGM
    -0.06
     siguientes
    -0.06
    tre
    -0.06
    evice
    -0.06
     расч
    -0.06
     کر
    -0.06
    POSITIVE LOGITS
     masculinity
    0.07
    ston
    0.06
    functional
    0.06
    /Documents
    0.06
    prisingly
    0.06
     Beginners
    0.06
    학
    0.06
     Dünya
    0.06
    ่างๆ
    0.06
    كور
    0.06
    Activations Density 0.068%

    No Known Activations