© 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. 57496
    Prev
    Next
    INDEX
    Explanations

    Legal context

    np_max-act · gemini-2.0-flash

    The neuron fires on legal discussion of procedural purposes—detecting functional verbs (e.g. “enable,” “provide,” “make,” “determine”) that introduce statements about what a court or process is meant to accomplish.

    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
    IDES
    -0.07
    OLT
    -0.07
    ides
    -0.06
    warts
    -0.06
    .finish
    -0.06
    .guard
    -0.06
    .ke
    -0.06
     bodies
    -0.06
    luğ
    -0.06
     suites
    -0.06
    POSITIVE LOGITS
     هنگام
    0.07
    _JO
    0.07
    ―
    0.06
     tasted
    0.06
     Clause
    0.06
     власності
    0.06
     Copyright
    0.06
    �州
    0.06
     enjoyed
    0.06
    -root
    0.06
    Activations Density 0.012%

    No Known Activations