© 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. 41634
    Prev
    Next
    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    This neuron detects law‐firm or attorney‐affiliation abbreviations (e.g. “PA,” “P.C.”) following lawyer names.

    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
    universal
    -0.07
    ्कर
    -0.06
    Towards
    -0.06
    �
    -0.06
     unterstüt
    -0.06
    _element
    -0.06
     C
    -0.06
    Mining
    -0.06
     stesso
    -0.06
    ึ้
    -0.06
    POSITIVE LOGITS
     umb
    0.06
     пояс
    0.06
    ист
    0.06
     нор
    0.06
    Enjoy
    0.06
    .Round
    0.06
    uble
    0.06
     ok
    0.06
    ]|
    0.05
    ाख
    0.05
    Activations Density 0.012%

    No Known Activations