© 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. 109361
    Prev
    Next
    INDEX
    Explanations

    stress

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of bodies of water or water-surrounded landforms (e.g. lakes, rivers, seas, tunnels/bridges separating land by water).

    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
     swims
    -0.07
     Websites
    -0.06
    یت
    -0.06
    بات
    -0.06
    萬
    -0.06
    syntax
    -0.06
    ظة
    -0.06
    _CR
    -0.06
    :request
    -0.06
    _complex
    -0.06
    POSITIVE LOGITS
    “He
    0.07
    //------------------------------------------------------------------------------↵↵
    0.07
    ///↵
    0.07
     승
    0.06
    çi
    0.06
     printers
    0.06
    óa
    0.06
    "He
    0.06
     MySqlConnection
    0.06
     g
    0.06
    Activations Density 0.212%

    No Known Activations