© 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. 68873
    Prev
    Next
    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash

    This neuron detects bibliographic citation elements, such as author initials, years, and journal/volume/page numbers.

    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
     favicon
    -0.06
    遍
    -0.06
    orial
    -0.06
    OUGH
    -0.06
    marker
    -0.06
    acity
    -0.06
    trag
    -0.06
    Prefs
    -0.06
    Pending
    -0.05
    loh
    -0.05
    POSITIVE LOGITS
     *\
    0.07
    .CenterScreen
    0.07
     HTMLElement
    0.07
     Fn
    0.07
     mpi
    0.07
     Ges
    0.06
     مت
    0.06
     handleSubmit
    0.06
    -lines
    0.06
    _CSS
    0.06
    Activations Density 0.011%

    No Known Activations