Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 109936
    Prev
    Next
    INDEX
    Explanations

    thoughts and opinions

    np_max-act · gemini-2.0-flash

    This neuron responds to common English function words (articles, pronouns, auxiliaries, and other high‐frequency stopwords) in running prose.

    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
     Beitrag
    -0.08
     thoát
    -0.07
     Stand
    -0.07
     parity
    -0.07
     bitte
    -0.06
     Yep
    -0.06
    731
    -0.06
    ae
    -0.06
    桃
    -0.06
     Inner
    -0.06
    POSITIVE LOGITS
     cận
    0.07
    >${
    0.07
    .textColor
    0.06
    (top
    0.06
     deren
    0.06
    (expect
    0.06
    _credit
    0.06
     ontvang
    0.06
    .student
    0.06
     tabel
    0.06
    Activations Density 0.080%

    No Known Activations