© 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. 126036
    Prev
    Next
    INDEX
    Explanations

    bracket

    np_max-act · gemini-2.0-flash

    The neuron is specialized to pick up square-bracketed placeholder fields (e.g. “[year]” or “[name of copyright owner]”) in license headers.

    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
     caregiver
    -0.08
     Ingredients
    -0.06
     Metro
    -0.06
    /callback
    -0.06
     france
    -0.06
     pudding
    -0.06
     Trường
    -0.06
    ?>>
    -0.06
    .Topic
    -0.06
     đầu
    -0.06
    POSITIVE LOGITS
    mour
    0.07
     minut
    0.07
     skies
    0.06
    adní
    0.06
    _dot
    0.06
     []
↵
    0.06
     raise
    0.06
     praise
    0.06
    .setStroke
    0.06
    şı
    0.06
    Activations Density 0.005%

    No Known Activations