© 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. 42534
    Prev
    Next
    INDEX
    Explanations

    count

    np_max-act · gemini-2.0-flash

    The neuron detects the phrasing of charge counts in legal opinions—specifically the “[number] count of” construction.

    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
     Corinthians
    -0.06
    [count
    -0.06
     Goku
    -0.06
     Wilkinson
    -0.06
    Yahoo
    -0.06
    Pipeline
    -0.06
    esco
    -0.06
     CONSEQUENTIAL
    -0.06
    ้าของ
    -0.06
    충
    -0.06
    POSITIVE LOGITS
    eceğiz
    0.07
     мер
    0.07
    _resolve
    0.06
    ']);
↵
    0.06
     listeners
    0.06
    .Shape
    0.06
    ตลอด
    0.06
    .appcompat
    0.06
    recipes
    0.06
    functions
    0.06
    Activations Density 0.003%

    No Known Activations