© 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. 13642
    Prev
    Next
    INDEX
    Explanations

    deals/ads/summaries

    np_max-act · gemini-2.0-flash

    This neuron detects numeric and quantitative promotional fine‐print details—things like expiration dates, dollar amounts, purchase limits, fees, and other numbers in deal terms.

    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
     категор
    -0.07
    _sync
    -0.07
    awan
    -0.06
    FullPath
    -0.06
     getVersion
    -0.06
    Annotation
    -0.06
     diferente
    -0.06
    .travel
    -0.06
     catchError
    -0.06
    external
    -0.06
    POSITIVE LOGITS
     tangled
    0.08
    Chan
    0.07
     CDs
    0.06
     noisy
    0.06
     Minist
    0.06
     DXGI
    0.06
     Modeling
    0.06
     gaan
    0.06
     plots
    0.06
     modeling
    0.05
    Activations Density 0.014%

    No Known Activations