© 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 EvalsExportsinterp-engineNEWAPI 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. 62416
    Prev
    Next
    INDEX
    Explanations

    terms related to statistical analysis and standard deviation

    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
    åĨµ
    -0.07
    ematic
    -0.07
    apore
    -0.07
    684
    -0.07
    Enlarge
    -0.07
    864
    -0.07
    æŁĦ
    -0.07
    oreach
    -0.06
    浪
    -0.06
    865
    -0.06
    POSITIVE LOGITS
     norm
    0.07
     Norm
    0.07
     Gaussian
    0.06
     beyond
    0.06
    :normal
    0.06
     Grade
    0.06
     Normal
    0.06
    norm
    0.06
    ritis
    0.06
     tails
    0.06
    Activations Density 0.047%

    No Known Activations