© 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. 42836
    Prev
    Next
    INDEX
    Explanations

    marital

    np_max-act · gemini-2.0-flash

    The neuron flags words referring to personal emotional or romantic relationship issues (e.g., “marital,” “troubles,” “hurt,” “romance”).

    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
     stress
    -0.06
     Wang
    -0.06
    prit
    -0.06
     由
    -0.06
     xếp
    -0.06
    澤
    -0.06
    ctest
    -0.06
    352
    -0.06
     Alejandro
    -0.06
     ANSI
    -0.06
    POSITIVE LOGITS
    _SECTION
    0.07
     isOpen
    0.07
     tek
    0.06
    _goto
    0.06
    tech
    0.06
    Como
    0.06
     HEL
    0.06
    .......
    0.06
     fought
    0.06
    ραν
    0.06
    Activations Density 0.217%

    No Known Activations