© 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. 17-LLAMASCOPE-RES-131K
    11. 106619
    Prev
    Next
    INDEX
    Explanations

    expressions of strong emphasis or focus on particular subjects

    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
    foon
    -0.08
     setResult
    -0.07
    unkt
    -0.07
    mouseup
    -0.07
    istung
    -0.07
    GLOBALS
    -0.07
    rouch
    -0.07
    setw
    -0.06
    emade
    -0.06
    _DEFIN
    -0.06
    POSITIVE LOGITS
     emphasis
    0.10
     importance
    0.08
     attention
    0.08
     effort
    0.07
     знаÑĩение
    0.07
     Importance
    0.07
     value
    0.07
     efforts
    0.07
     focus
    0.07
     знаÑĩениÑı
    0.07
    Activations Density 0.014%

    No Known Activations