© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 126130
    Prev
    Next
    INDEX
    Explanations

    hysteresis

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the term “hysteresis” (and its inflected forms) in the text.

    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
    uild
    -0.06
    Serve
    -0.06
     vouchers
    -0.06
    pivot
    -0.06
     cairo
    -0.06
     add
    -0.06
     upgrades
    -0.06
     occurrences
    -0.06
     Sunset
    -0.06
    mind
    -0.06
    POSITIVE LOGITS
     hyster
    0.07
     bueno
    0.06
    ológ
    0.06
    шую
    0.06
    الية
    0.06
     пы
    0.06
     proj
    0.06
     histó
    0.06
    шем
    0.06
     tarihinde
    0.06
    Activations Density 0.001%

    No Known Activations