© 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. 60990
    Prev
    Next
    INDEX
    Explanations

    terms related to organizational structures and systems

    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
    ìĿ´ëĤĺ
    -0.09
    ãĤĵãģ¨
    -0.08
    æĪĸèĢħ
    -0.08
    ë¥´ê³ł
    -0.08
    FRING
    -0.08
     æĪĸ
    -0.08
    ãģ¾ãģļ
    -0.08
    ê±°ëĤĺ
    -0.07
    ãĤĬãģ¨
    -0.07
    æĪĸ
    -0.07
    POSITIVE LOGITS
     alike
    0.29
     respectively
    0.14
     olmak
    0.10
     ÑģооÑĤвеÑĤ
    0.08
     sides
    0.07
    /etc
    0.07
     serta
    0.07
     depending
    0.07
    depending
    0.07
     versions
    0.07
    Activations Density 0.045%

    No Known Activations