© 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. 7845
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    The neuron detects the characteristic opening sentence of a court opinion that frames the legal question (e.g. “This case requires us to…,” “This case presents…”).

    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
    etas
    -0.07
     getRandom
    -0.06
     dikke
    -0.06
     Yine
    -0.06
    iske
    -0.06
     humanities
    -0.06
    //----------------
    -0.06
    '||
    -0.06
     ymin
    -0.06
     cafes
    -0.06
    POSITIVE LOGITS
     loc
    0.06
    usable
    0.06
     dział
    0.06
    eneric
    0.06
     felon
    0.06
    Hash
    0.06
     Cron
    0.06
    973
    0.06
     rules
    0.06
    cerer
    0.06
    Activations Density 0.013%

    No Known Activations