© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 57620
    Prev
    Next
    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash

    This neuron detects category labels for National Register of Historic Places listings specifying a particular county and state.

    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
    '],
↵
    -0.07
    Senate
    -0.07
    .Registry
    -0.07
     från
    -0.06
     contraceptive
    -0.06
     differs
    -0.06
    .exist
    -0.06
    .Unit
    -0.06
    FileSystem
    -0.06
    Football
    -0.06
    POSITIVE LOGITS
    .rm
    0.07
     evacuated
    0.06
     strav
    0.06
     دقیق
    0.06
    ानद
    0.06
    aim
    0.06
    Course
    0.06
    akter
    0.06
    itin
    0.06
     将
    0.06
    Activations Density 0.001%

    No Known Activations