© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 76080
    Prev
    Next
    INDEX
    Explanations

    terms related to machinery and manufacturing processes

    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
    asics
    -0.07
    ibles
    -0.07
     compat
    -0.07
     vign
    -0.07
    phan
    -0.07
    vang
    -0.06
    祥
    -0.06
    oth
    -0.06
    extras
    -0.06
    claimer
    -0.06
    POSITIVE LOGITS
    .alibaba
    0.07
     Heller
    0.07
    egative
    0.06
     Wid
    0.06
     indoor
    0.06
    $MESS
    0.06
    orra
    0.06
    ashboard
    0.06
    /tags
    0.06
     Gerr
    0.06
    Activations Density 0.012%

    No Known Activations