© 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. 17-LLAMASCOPE-RES-131K
    6. 3870
    Prev
    Next
    INDEX
    Explanations

    references to the concept of global dominance or influence

    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
    ÑĢÑİ
    -0.07
     patch
    -0.06
     mül
    -0.06
    patch
    -0.06
     Reign
    -0.06
     Locator
    -0.06
     hoá
    -0.06
    _patch
    -0.06
     PATCH
    -0.06
     Patch
    -0.06
    POSITIVE LOGITS
    imed
    0.06
    esion
    0.06
    enser
    0.06
    izr
    0.06
    mey
    0.06
    ometr
    0.06
    lama
    0.06
    ippi
    0.06
    egie
    0.06
    езÑĥлÑĮÑĤ
    0.06
    Activations Density 0.000%

    No Known Activations