© 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. 44422
    Prev
    Next
    INDEX
    Explanations

    >

    np_max-act · gemini-2.0-flash

    The neuron is keyed to XML/HTML markup elements (tags, attribute names, and syntax like “<”, “>”, “id”, “link”, 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
    änd
    -0.07
     egret
    -0.06
     Ey
    -0.06
    Exec
    -0.06
     setter
    -0.06
     ş
    -0.06
    Acc
    -0.06
     Clips
    -0.06
    /ns
    -0.06
    _water
    -0.06
    POSITIVE LOGITS
     حکم
    0.07
     currentPage
    0.06
    ograms
    0.06
    plied
    0.06
    pleted
    0.06
    _BITMAP
    0.06
    ी,
    0.06
    (UIAlertAction
    0.06
    μου
    0.06
    _SOURCE
    0.06
    Activations Density 0.003%

    No Known Activations