© 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. 125276
    Prev
    Next
    INDEX
    Explanations

    sir

    np_max-act · gemini-2.0-flash

    The neuron fires on the placeholder character‐name tokens (e.g. “NAME_1,” “NAME_2,” etc.), in particular when they’re used in dialogue attributions.

    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
    _DIALOG
    -0.06
     CircularProgressIndicator
    -0.06
     adequate
    -0.06
     grinned
    -0.06
     jealous
    -0.06
     лечения
    -0.06
    хів
    -0.06
     리스트
    -0.06
    oš
    -0.06
     Stock
    -0.05
    POSITIVE LOGITS
     उच
    0.07
    ГО
    0.07
    ype
    0.07
    /state
    0.07
    /****************************************************************************
    0.07
    �
    0.07
     nastav
    0.07
     assemble
    0.06
    (workspace
    0.06
     bands
    0.06
    Activations Density 0.013%

    No Known Activations