Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 75076
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to food preparation and culinary usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gir
    -0.07
    eus
    -0.07
    İ·
    -0.07
    íĦ¸
    -0.06
    ContentLoaded
    -0.06
    _THAN
    -0.06
    affle
    -0.06
    fas
    -0.06
    LOUD
    -0.06
    ilk
    -0.06
    POSITIVE LOGITS
    lund
    0.07
    ÑİÑĢ
    0.06
    arkan
    0.06
     grav
    0.06
     Mixed
    0.06
    Į¨
    0.06
    MLElement
    0.06
    reesome
    0.06
     itemprop
    0.06
    rieg
    0.06
    Activations Density 0.031%

    No Known Activations