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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 60879
    Prev
    Next
    INDEX
    Explanations

    technical terms and parameters related to programming and system functions

    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
    uno
    -0.07
    afa
    -0.07
    rieb
    -0.07
    -urlencoded
    -0.07
    /Foundation
    -0.07
    aille
    -0.07
    undler
    -0.07
    ledi
    -0.07
    Schedulers
    -0.07
    _CUDA
    -0.07
    POSITIVE LOGITS
     instead
    0.09
     Instead
    0.08
    instead
    0.08
    Instead
    0.06
     extra
    0.06
     only
    0.06
    Mode
    0.06
     output
    0.06
    eya
    0.06
     Silver
    0.06
    Activations Density 0.032%

    No Known Activations