© 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. 130627
    Prev
    Next
    INDEX
    Explanations

    technical terms and jargon related to networking and computing

    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
    /environment
    -0.06
    reation
    -0.06
    /security
    -0.06
    rientation
    -0.06
     Sloan
    -0.06
    æ¡IJ
    -0.06
    -specific
    -0.06
    quest
    -0.06
     Shim
    -0.06
    pga
    -0.06
    POSITIVE LOGITS
    -based
    0.20
    -Based
    0.18
    based
    0.15
    _based
    0.13
    å¼ı
    0.12
    Based
    0.12
    ãģ«ãĤĪãĤĭ
    0.11
     기ë°ĺ
    0.10
     based
    0.10
    -mediated
    0.10
    Activations Density 0.258%

    No Known Activations