© 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. 130734
    Prev
    Next
    INDEX
    Explanations

    references to datasets and statistical evaluations in research papers

    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
    UBE
    -0.06
     Pdf
    -0.06
     patented
    -0.06
     Bett
    -0.05
     pdf
    -0.05
    705
    -0.05
    adium
    -0.05
    497
    -0.05
     s
    -0.05
    pdf
    -0.05
    POSITIVE LOGITS
     dataset
    0.11
     Dataset
    0.10
    dataset
    0.10
    .dataset
    0.08
     datasets
    0.08
    senal
    0.08
    ubat
    0.08
    Neutral
    0.08
     DataSet
    0.08
    æk
    0.08
    Activations Density 0.021%

    No Known Activations