© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 6796
    Prev
    Next
    INDEX
    Explanations

    );

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric citation tokens – specifically the volume/page numbers (including decimals) in legal case citations.

    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
    َى
    -0.07
    >Total
    -0.07
    Updating
    -0.07
    Cancelled
    -0.07
    .Ribbon
    -0.06
    Commercial
    -0.06
     Planned
    -0.06
    硬
    -0.06
    telefono
    -0.06
    ymmetric
    -0.06
    POSITIVE LOGITS
    Model
    0.07
    pha
    0.06
    }/${
    0.06
    StyleSheet
    0.06
    _dp
    0.06
    如此
    0.06
    trieve
    0.06
    (tree
    0.06
    .Environment
    0.06
    كان
    0.05
    Activations Density 0.002%

    No Known Activations