Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 42211
    Prev
    Next
    INDEX
    Explanations

    rooms in a house

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric mentions of property features—counts of rooms, bedrooms, kitchens, baths, etc.

    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
    URY
    -0.07
     Package
    -0.07
    _bad
    -0.06
    kový
    -0.06
    .hex
    -0.06
     Electrical
    -0.06
     baked
    -0.06
    Props
    -0.06
     finest
    -0.06
     believer
    -0.06
    POSITIVE LOGITS
    //*[@
    0.07
    正式
    0.07
     trọng
    0.07
     tableLayoutPanel
    0.07
    ……。
    0.06
    цієн
    0.06
     ΠΑΝ
    0.06
     feder
    0.06
     harb
    0.06
    .ToolStripSeparator
    0.06
    Activations Density 0.127%

    No Known Activations