© 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. 91620
    Prev
    Next
    INDEX
    Explanations

    Usage instructions

    np_max-act · gemini-2.0-flash

    This neuron detects list‐item enumeration markers (e.g. “1.”, “2.”, “Use”, “First”, “Second”) in step‐by‐step instructions.

    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
    549
    -0.06
    oundingBox
    -0.06
    icas
    -0.06
     concerts
    -0.06
     Ske
    -0.06
     entering
    -0.06
     displ
    -0.06
     sailors
    -0.06
    ivers
    -0.06
     timer
    -0.06
    POSITIVE LOGITS
    لیل
    0.07
    (poly
    0.07
    ことに
    0.07
     requestData
    0.07
     convictions
    0.07
    ‌د
    0.06
    ouch
    0.06
    خرید
    0.06
     Совет
    0.06
     çocuk
    0.06
    Activations Density 0.050%

    No Known Activations