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

    Neuronpedia

    Jacobian LensNEW
    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. 15-LLAMASCOPE-RES-131K
    11. 88028
    Prev
    Next
    INDEX
    Explanations

    numerical statistics related to sports performance

    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
    arf
    -0.08
    lyn
    -0.07
    ł
    -0.07
    åĴ²
    -0.07
    ứt
    -0.07
     обÑĢаз
    -0.07
    ÂŁ
    -0.07
    _OT
    -0.07
     szcz
    -0.07
    ardon
    -0.06
    POSITIVE LOGITS
    gere
    0.06
     enlist
    0.05
    iant
    0.05
     exert
    0.05
     reversed
    0.05
    åĪĨ
    0.05
    pow
    0.05
     Vert
    0.05
    athing
    0.05
     win
    0.05
    Activations Density 0.006%

    No Known Activations