© 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. 92542
    Prev
    Next
    INDEX
    Explanations

    phrases related to academic or learning contexts

    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
     kıs
    -0.08
    뮤
    -0.07
    ´Ī
    -0.07
     Bylo
    -0.07
    .portal
    -0.07
    Když
    -0.07
    ä¸Ģ度
    -0.07
    Ïĩι
    -0.07
     arac
    -0.07
    imore
    -0.07
    POSITIVE LOGITS
     usually
    0.10
     it
    0.10
    usually
    0.08
     often
    0.08
     Usually
    0.07
     typically
    0.07
     either
    0.07
    Usually
    0.06
     tends
    0.06
     only
    0.06
    Activations Density 0.033%

    No Known Activations