© 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. 78394
    Prev
    Next
    INDEX
    Explanations

    references to the Ubuntu operating system and related distributions

    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
    usc
    -0.07
    lessly
    -0.07
    kul
    -0.07
     Borough
    -0.06
    pos
    -0.06
    ctor
    -0.06
     Palmer
    -0.06
    kova
    -0.06
    ToBounds
    -0.06
    poz
    -0.06
    POSITIVE LOGITS
    -gnu
    0.07
    PPP
    0.07
    _FRE
    0.07
    Skeleton
    0.07
    Å©
    0.07
    -standard
    0.07
    ¼
    0.07
    Verifier
    0.07
    maze
    0.07
    -origin
    0.06
    Activations Density 0.003%

    No Known Activations