Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 91426
    Prev
    Next
    INDEX
    Explanations

    (b

    np_max-act · gemini-2.0-flash

    This neuron identifies references to statutory code sections, guideline citations, and similar legal citation markers (e.g. “21 U.S.C. § 841(b)(1)(A)”).

    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
     ça
    -0.06
     Mug
    -0.06
     Wood
    -0.06
     Maison
    -0.06
     Continent
    -0.06
     lends
    -0.06
    Roger
    -0.06
     prostřednictvím
    -0.06
     MJ
    -0.06
    SHIP
    -0.06
    POSITIVE LOGITS
     sociální
    0.07
    _VARIABLE
    0.06
    enticator
    0.06
     thi
    0.06
    aternion
    0.06
    _GUID
    0.06
    _main
    0.06
     accr
    0.06
    ati
    0.06
    interrupt
    0.06
    Activations Density 0.001%

    No Known Activations