© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 129983
    Prev
    Next
    INDEX
    Explanations

    project

    np_max-act · gemini-2.0-flash

    the neuron primarily detects occurrences of the word “project” (especially in contexts like “project” or “project manager”).

    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
    Ar
    -0.07
    cala
    -0.06
    HEIGHT
    -0.06
    uty
    -0.06
    Kid
    -0.06
     Minist
    -0.06
    CAST
    -0.06
    cut
    -0.06
    .dataSource
    -0.06
    需求
    -0.06
    POSITIVE LOGITS
     apa
    0.07
     кле
    0.06
     harsh
    0.06
     velký
    0.06
    sim
    0.06
    	point
    0.06
     kém
    0.06
    ньо
    0.06
     bonus
    0.06
     컴
    0.06
    Activations Density 0.016%

    No Known Activations