© 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. 91703
    Prev
    Next
    INDEX
    Explanations

    proofreading or checking

    np_max-act · gemini-2.0-flash

    This neuron detects numbered step markers (e.g., list item prefixes like “1.”, “2.”) in instructional content.

    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
     Jeremiah
    -0.07
    emiah
    -0.06
     transporter
    -0.06
     mush
    -0.06
    ुण
    -0.06
    _↵↵
    -0.06
     Osama
    -0.06
     Neo
    -0.06
     rotary
    -0.06
    cook
    -0.06
    POSITIVE LOGITS
    bufio
    0.07
     POLL
    0.07
     εκ
    0.07
    .inspect
    0.07
    akest
    0.06
    管理员
    0.06
     PCR
    0.06
    (Gtk
    0.06
     gén
    0.06
    рон
    0.06
    Activations Density 0.034%

    No Known Activations