© 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. 5-LLAMASCOPE-RES-131K
    11. 126448
    Prev
    Next
    INDEX
    Explanations

    mentions of dimensions and dimensionality in contexts related to geometry or algorithms

    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
    евиÑĩ
    -0.06
    empo
    -0.06
    ed
    -0.06
    çİĩ
    -0.06
    евÑĸ
    -0.06
     ÑĤÑĢан
    -0.06
     Claus
    -0.06
     enough
    -0.06
    yc
    -0.06
    daily
    -0.05
    POSITIVE LOGITS
    ɵ
    0.07
    anden
    0.07
    iversary
    0.07
    fen
    0.07
    awah
    0.06
    ÄĮesk
    0.06
    cheduler
    0.06
    MSN
    0.06
     Fen
    0.06
    /format
    0.06
    Activations Density 0.001%

    No Known Activations