© 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. 56721
    Prev
    Next
    INDEX
    Explanations

    legal citations

    np_max-act · gemini-2.0-flash

    This neuron detects legal case citations (volume and reporter references, e.g., “S.Ct.” and associated numbers).

    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
     showAlert
    -0.07
    (mappedBy
    -0.07
    ニニ
    -0.06
    SetText
    -0.06
    devil
    -0.06
    solution
    -0.06
     срав
    -0.06
     ridden
    -0.06
     heute
    -0.06
    іту
    -0.06
    POSITIVE LOGITS
     Cork
    0.06
     );
    0.06
    .serializer
    0.06
    !")
    0.06
    (sym
    0.06
    [p
    0.06
    Ré
    0.06
    ond
    0.06
    .Enable
    0.06
    ()))↵
    0.06
    Activations Density 0.000%

    No Known Activations