© 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 EvalsExportsinterp-engineNEWAPI 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. 105455
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate inclusion or limitations in legal and software contexts

    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
     hone
    -0.06
    LOB
    -0.06
    hower
    -0.06
    leur
    -0.06
    680
    -0.06
    eneg
    -0.06
    igan
    -0.06
    aper
    -0.06
     ConfigureServices
    -0.06
    CU
    -0.06
    POSITIVE LOGITS
     Rag
    0.08
     æį
    0.07
    .nano
    0.07
    elf
    0.07
    _codegen
    0.07
    ries
    0.06
    koa
    0.06
    ilim
    0.06
     Sah
    0.06
    isphere
    0.06
    Activations Density 0.001%

    No Known Activations