© 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. 58490
    Prev
    Next
    INDEX
    Explanations

    technical file handling and programming concepts

    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
    erez
    -0.07
     Shel
    -0.06
    ucc
    -0.06
    olle
    -0.06
    aju
    -0.06
    024
    -0.06
    allest
    -0.06
    ogi
    -0.06
    aidu
    -0.06
    _ISS
    -0.06
    POSITIVE LOGITS
    EXT
    0.06
    reh
    0.06
    ãģĺ
    0.06
    ecurity
    0.06
     doubt
    0.06
    urtle
    0.06
    Å¡et
    0.06
    FSIZE
    0.06
    kish
    0.06
    mtree
    0.06
    Activations Density 0.000%

    No Known Activations