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

    Neuronpedia

    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. 74538
    Prev
    Next
    INDEX
    Explanations

    occurrences of domain names and their relevance in a technical context

    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
    loff
    -0.06
     ör
    -0.06
    Scrollbar
    -0.06
     Tra
    -0.06
     Introduction
    -0.06
    гÑĢад
    -0.06
    gend
    -0.06
    PLEX
    -0.06
    icha
    -0.06
    ãģĹãģ¾ãģ£ãģŁ
    -0.05
    POSITIVE LOGITS
    fak
    0.07
    ovsky
    0.07
    UME
    0.06
    ERSHEY
    0.06
    uni
    0.06
    _mob
    0.06
    ancellable
    0.06
    еÑĤÑĮ
    0.06
     Nez
    0.06
    ersions
    0.06
    Activations Density 0.000%

    No Known Activations