© 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. 109438
    Prev
    Next
    INDEX
    Explanations

    research papers

    np_max-act · gemini-2.0-flash

    The neuron activates on tokens that describe research methods or study actions (e.g. “we prove,” “using,” “paper continues,” “investigate”).

    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
     >
    -0.07
     regained
    -0.07
    内部
    -0.06
     NVIDIA
    -0.06
     استخدام
    -0.06
     家
    -0.06
     Yo
    -0.06
     sprung
    -0.06
    ubar
    -0.06
     webcam
    -0.06
    POSITIVE LOGITS
    론
    0.07
    predicate
    0.06
    Iterable
    0.06
    hound
    0.06
    Processes
    0.06
     Sax
    0.06
    ریق
    0.06
     addTarget
    0.06
     dříve
    0.06
     فرو
    0.06
    Activations Density 0.176%

    No Known Activations