© 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. 91960
    Prev
    Next
    INDEX
    Explanations

    ite

    np_max-act · gemini-2.0-flash

    The neuron detects bracketed case‐citation markers (e.g. “[Cite as …]”) in legal‐opinion 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
     RecognitionException
    -0.06
    Rating
    -0.06
    getActiveSheet
    -0.06
     ราย
    -0.06
     BufferedImage
    -0.06
     sağlık
    -0.06
     ев
    -0.06
     Arthropoda
    -0.06
    راف
    -0.06
    ิงหาคม
    -0.06
    POSITIVE LOGITS
    Analy
    0.07
     convey
    0.07
    arguments
    0.07
     primaries
    0.07
     sevent
    0.07
    _charset
    0.07
     proph
    0.07
    做
    0.06
     gentle
    0.06
     Společ
    0.06
    Activations Density 0.000%

    No Known Activations