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

    Neuronpedia

    Jacobian LensNEW
    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. 82832
    Prev
    Next
    INDEX
    Explanations

    terms related to materials used in manufacturing and their applications

    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
     Copper
    -0.07
    hammer
    -0.06
    a
    -0.06
    id
    -0.06
     prote
    -0.06
     hammer
    -0.06
    arching
    -0.05
     Hamilton
    -0.05
    ↵
    -0.05
     metals
    -0.05
    POSITIVE LOGITS
     carbon
    0.10
    ILON
    0.09
     Carbon
    0.09
    carbon
    0.09
    Carbon
    0.09
    bette
    0.08
    /graph
    0.08
    ãģ¡ãģ¯
    0.08
    .Graph
    0.07
     chatte
    0.07
    Activations Density 0.006%

    No Known Activations