© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 27039
    Prev
    Next
    INDEX
    Explanations

    references to constraints or limitations within a system or 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
     Progress
    -0.06
    vern
    -0.06
    illo
    -0.06
    isco
    -0.06
    ãĥªãĥ¼ãĤº
    -0.06
    Means
    -0.06
    .vm
    -0.06
    metatable
    -0.06
    UV
    -0.06
    esModule
    -0.06
    POSITIVE LOGITS
    Ñĥже
    0.07
     already
    0.07
     present
    0.07
    kup
    0.07
    ensi
    0.07
     ÄIJá»ĵng
    0.07
    already
    0.06
     StringComparison
    0.06
     among
    0.06
    currently
    0.06
    Activations Density 0.019%

    No Known Activations