© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 109091
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of an industry context—especially phrases referring to “chemical industry.”

    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
     terk
    -0.07
    üre
    -0.07
     getStatus
    -0.06
     سخن
    -0.06
     december
    -0.06
    -compatible
    -0.06
     Nicola
    -0.06
     mãe
    -0.06
    please
    -0.06
    Salary
    -0.06
    POSITIVE LOGITS
     Gratuit
    0.07
    _attempts
    0.07
    (new
    0.07
    示
    0.06
    allo
    0.06
    اهم
    0.06
    ference
    0.06
    。</
    0.06
    _SURFACE
    0.06
    arpa
    0.06
    Activations Density 0.035%

    No Known Activations