© 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. 29606
    Prev
    Next
    INDEX
    Explanations

    quantitative data related to measurements and financial figures

    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
    .SDK
    -0.07
    engu
    -0.07
    acus
    -0.07
    ìĽĥ
    -0.07
    rene
    -0.07
    ContentPane
    -0.07
    -пÑĢав
    -0.07
    ابد
    -0.06
    ilater
    -0.06
    ละ
    -0.06
    POSITIVE LOGITS
     altogether
    0.10
     collective
    0.09
     total
    0.08
     collectively
    0.08
     overall
    0.07
    جÙħÙĪع
    0.07
     combined
    0.07
     ÙħجÙħÙĪع
    0.07
     Collective
    0.06
    æĢ»
    0.06
    Activations Density 0.023%

    No Known Activations