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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 110458
    Prev
    Next
    INDEX
    Explanations

    Legal documents

    np_max-act · gemini-2.0-flash

    The neuron activates on numerical references in legal text—particularly statute and section numbers, years, and other citation figures.

    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
    _RX
    -0.06
     Crunch
    -0.06
    -tier
    -0.06
    MV
    -0.06
     retirement
    -0.06
    ole
    -0.06
     LDAP
    -0.06
    ust
    -0.06
    _ctxt
    -0.06
    ож
    -0.06
    POSITIVE LOGITS
    。此
    0.07
    ョ
    0.07
    .Dialog
    0.07
    (Thread
    0.06
    \Requests
    0.06
    .setStroke
    0.06
    開始
    0.06
    curity
    0.06
    ються
    0.06
    .layout
    0.06
    Activations Density 0.061%

    No Known Activations