© 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. 43393
    Prev
    Next
    INDEX
    Explanations

    rokes

    np_max-act · gemini-2.0-flash

    terms related to advanced concepts in business strategy and technology.

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

    The neuron is detecting high-intensity “power” buzzwords (e.g. Hyper, Advanced, Mastery, Amplification) typically used in marketing-style keyword combinations.

    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
     مشاه
    -0.07
     Mr
    -0.07
    productName
    -0.07
    ्च
    -0.06
    _delegate
    -0.06
    Mr
    -0.06
     Eg
    -0.06
     Cock
    -0.06
    .componentInstance
    -0.06
     بیشتری
    -0.06
    POSITIVE LOGITS
    /job
    0.07
    沒有
    0.06
    ै?↵
    0.06
     Evidence
    0.06
     encountering
    0.06
    Evidence
    0.06
    Browse
    0.06
     flushing
    0.06
     Wisdom
    0.06
    Computed
    0.06
    Activations Density 12.068%

    No Known Activations