© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 38323
    Prev
    Next
    INDEX
    Explanations

    legal liability

    np_max-act · gemini-2.0-flash

    This neuron detects language specifying legal liability or responsibility (e.g., words like “liable,” “held,” or “responsible”).

    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
     Rabbi
    -0.07
    ";
    -0.06
    \">";↵
    -0.06
    �
    -0.06
    (padding
    -0.06
     MyBase
    -0.06
    안마
    -0.06
     Ket
    -0.06
     کننده
    -0.06
    ็กชาย
    -0.05
    POSITIVE LOGITS
    _lookup
    0.08
     sola
    0.07
     palavra
    0.07
     Associated
    0.07
    major
    0.06
    652
    0.06
     ç
    0.06
     inspir
    0.06
    _weight
    0.06
     bands
    0.06
    Activations Density 0.029%

    No Known Activations