© 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
    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. 109166
    Prev
    Next
    INDEX
    Explanations

    rules

    np_max-act · gemini-2.0-flash

    The neuron is triggered by formal legal‐procedure rule citations (e.g. “Rule X,” “Rules of Civil Procedure,” etc.).

    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
     праці
    -0.07
     vede
    -0.06
     Peg
    -0.06
     redundancy
    -0.06
     Charset
    -0.06
     Παρα
    -0.06
     Circuit
    -0.06
    िड
    -0.06
    ，当
    -0.06
     sond
    -0.06
    POSITIVE LOGITS
     तल
    0.08
     BAB
    0.07
    び
    0.07
    */
↵
    0.07
     रख
    0.07
    -L
    0.07
    ($("#
    0.07
    oram
    0.07
    śli
    0.07
    ी
    0.06
    Activations Density 0.002%

    No Known Activations