© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 61508
    Prev
    Next
    INDEX
    Explanations

    modeling and analysis concepts related to computational and biological systems and their dynamics

    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
    äº
    -0.07
    еÑģÑı
    -0.06
    енÑģ
    -0.06
    foreground
    -0.06
    ç´Ģ
    -0.06
    :hidden
    -0.06
     forme
    -0.06
    éĤ£éĩĮ
    -0.06
    vod
    -0.06
    Span
    -0.06
    POSITIVE LOGITS
     dynamics
    0.10
     interactions
    0.09
     Dynamics
    0.08
     scenarios
    0.08
     scenario
    0.08
    uggy
    0.08
    ynamics
    0.07
    ogenesis
    0.07
     processes
    0.07
    issy
    0.07
    Activations Density 0.087%

    No Known Activations