© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 73752
    Prev
    Next
    INDEX
    Explanations

    UD

    np_max-act · gemini-2.0-flash

    This neuron detects the “UD” labels and associated dataset‐header tokens (e.g. “UD_<…>”) in the document’s metadata or section titles.

    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
    okers
    -0.06
    /Search
    -0.06
    Disallow
    -0.06
    ises
    -0.06
    Day
    -0.06
    Gate
    -0.06
     oceans
    -0.06
     PAC
    -0.06
     nemá
    -0.06
     Ti
    -0.06
    POSITIVE LOGITS
    ие
    0.07
    [type
    0.07
     вниз
    0.07
     слова
    0.06
    .rstrip
    0.06
     ∀
    0.06
     trying
    0.06
     saddened
    0.06
    alted
    0.06
    own
    0.06
    Activations Density 0.001%

    No Known Activations