© 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. 129752
    Prev
    Next
    INDEX
    Explanations

    Sure

    np_max-act · gemini-2.0-flash

    The neuron fires on the polite acknowledgement at the start of assistant replies (e.g. “Sure,” or similar opening phrase).

    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
     advant
    -0.06
    _arrow
    -0.06
     realiz
    -0.06
     푸
    -0.06
    _ACTIVE
    -0.06
     Rwanda
    -0.06
    anager
    -0.06
    MainThread
    -0.06
    205
    -0.05
     выдел
    -0.05
    POSITIVE LOGITS
    ()."
    0.08
    ?\
    0.07
     cung
    0.07
    /Edit
    0.07
    .Matrix
    0.07
    ...,
    0.07
     Interested
    0.07
     tasty
    0.06
     Francie
    0.06
     questioned
    0.06
    Activations Density 0.034%

    No Known Activations