© 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. 40777
    Prev
    Next
    INDEX
    Explanations

    concepts related to connectivity and independence in a networked environment

    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
    hev
    -0.07
    ANGLES
    -0.07
     createAction
    -0.07
    -thumbnails
    -0.07
     ÑģобÑĸ
    -0.06
    .constructor
    -0.06
    æĪı
    -0.06
    ÙĪسÛĮ
    -0.06
    oni
    -0.06
    oma
    -0.06
    POSITIVE LOGITS
    ä¸ĢåĪĩ
    0.08
     everything
    0.07
    everything
    0.07
     vice
    0.06
    ToolStrip
    0.06
     Vice
    0.06
     Cycl
    0.06
    vail
    0.06
    orde
    0.06
    æīĢæľī
    0.06
    Activations Density 0.029%

    No Known Activations