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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 89019
    Prev
    Next
    INDEX
    Explanations

    patents and applications

    np_max-act · gemini-2.0-flash

    The neuron activates on the detailed description of “patent claims” – the section explaining what patent claims are and defining their scope.

    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
    elic
    -0.08
    اتی
    -0.06
     hearings
    -0.06
    通過
    -0.06
    knife
    -0.06
    納
    -0.05
     PASS
    -0.05
    ']);
↵
    -0.05
    -0.05
    接着
    -0.05
    POSITIVE LOGITS
    @register
    0.07
    |null
    0.07
     Modular
    0.07
     Sq
    0.07
    _DEST
    0.07
    شناسی
    0.06
    ILLA
    0.06
    >'.
    0.06
    _singular
    0.06
    vers
    0.06
    Activations Density 0.013%

    No Known Activations