© 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. 92533
    Prev
    Next
    INDEX
    Explanations

    technical language

    np_max-act · gemini-2.0-flash

    inventions related to automotive safety features, specifically airbag systems and their activation mechanisms.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron activates on occurrences of “row” or “rows” (as in planting rows or furrows).

    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
     sensors
    -0.07
    Japan
    -0.06
    uyễn
    -0.06
     پرداز
    -0.06
    heart
    -0.06
     pager
    -0.06
    manager
    -0.06
    елів
    -0.06
    Russia
    -0.06
    agement
    -0.06
    POSITIVE LOGITS
    .localScale
    0.07
    IGNED
    0.06
    claimed
    0.06
    説
    0.06
    Χ
    0.06
    比较
    0.06
     tí
    0.06
    搜
    0.06
    _DIRECT
    0.06
    _stamp
    0.06
    Activations Density 0.215%

    No Known Activations