© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 125010
    Prev
    Next
    INDEX
    Explanations

    Suspenseful, unresolved questions

    np_max-act · gemini-2.0-flash

    This neuron fires on end-of-sentence markers and tokens that signal an open-ended or cliffhanger ending (e.g. periods, question marks, “open”, “-ended”, etc.).

    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
    porno
    -0.07
    ?>↵
    -0.06
     yahoo
    -0.06
     exclusive
    -0.06
     rally
    -0.06
    ़्
    -0.06
     کرده
    -0.06
     niche
    -0.06
    Porno
    -0.06
     york
    -0.06
    POSITIVE LOGITS
    velle
    0.08
    rays
    0.07
     Vegas
    0.06
    MimeType
    0.06
     receipts
    0.06
     Wordpress
    0.06
    (INT
    0.06
    ************************
    0.06
    .dispatcher
    0.06
    _REL
    0.06
    Activations Density 0.039%

    No Known Activations