© 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. 56567
    Prev
    Next
    INDEX
    Explanations

    technical terms related to statistical analysis and uncertainty estimation

    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
    å°ij女
    -0.07
    zem
    -0.07
    rary
    -0.07
    aret
    -0.07
    ucci
    -0.06
    öyle
    -0.06
    :convert
    -0.06
    zcze
    -0.06
    ipay
    -0.06
     RaycastHit
    -0.06
    POSITIVE LOGITS
     variance
    0.11
    .std
    0.09
     covariance
    0.09
     var
    0.09
     Cov
    0.08
    istrovstvÃŃ
    0.08
     std
    0.08
     Var
    0.08
    Æ¡
    0.07
     cov
    0.07
    Activations Density 0.320%

    No Known Activations