© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 56014
    Prev
    Next
    INDEX
    Explanations

    ose

    np_max-act · gemini-2.0-flash

    The neuron detects dosage terms, especially the word “dose” (often in “high-dose” treatment contexts).

    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
     patterns
    -0.06
    GridLayout
    -0.06
     Management
    -0.06
     ledger
    -0.06
    BILE
    -0.06
    nos
    -0.06
     technical
    -0.06
     advertisement
    -0.06
     Meat
    -0.06
    ケット
    -0.06
    POSITIVE LOGITS
    ‌المللی
    0.06
     moci
    0.06
     trouvé
    0.06
    __',
    0.06
    unakan
    0.06
    这里
    0.06
     LOW
    0.06
    υκ
    0.06
    someone
    0.06
    .test
    0.06
    Activations Density 0.002%

    No Known Activations