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. 77316
    Prev
    Next
    INDEX
    Explanations

    terms related to products or materials, specifically in the context of manufacturing or inventory

    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
    ancellation
    -0.07
    lobs
    -0.07
     pedal
    -0.06
     stockings
    -0.06
    dre
    -0.06
    amon
    -0.06
     tela
    -0.06
    磨
    -0.06
    лл
    -0.06
     pedals
    -0.06
    POSITIVE LOGITS
     packaging
    0.09
     Packaging
    0.09
    irt
    0.07
     Kraft
    0.07
    Âŀ
    0.07
    Serialization
    0.07
    Pack
    0.07
     packing
    0.06
    _CPU
    0.06
     Serialization
    0.06
    Activations Density 0.009%

    No Known Activations