© 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. 76322
    Prev
    Next
    INDEX
    Explanations

    business demand

    np_max-act · gemini-2.0-flash

    The neuron reliably fires on language used to describe market‐oriented forecasts—terms about demand, expectations, and projected growth.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    chemical compounds and their applications in various industries.

    oai_token-act-pair · gpt-4o-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
    _MUT
    -0.07
    TypeDef
    -0.07
    れた
    -0.06
     vending
    -0.06
    树
    -0.06
    (My
    -0.06
    recursive
    -0.06
    Usage
    -0.06
     mappedBy
    -0.06
    "bytes
    -0.06
    POSITIVE LOGITS
     fantast
    0.06
     ребенка
    0.06
     firearm
    0.06
    ка
    0.06
    وف
    0.06
    atra
    0.06
     страниц
    0.06
    έργ
    0.06
     environ
    0.06
    ynos
    0.06
    Activations Density 0.022%

    No Known Activations