© 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. 106570
    Prev
    Next
    INDEX
    Explanations

    technical terms and specific nouns related to databases and architecture

    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
    isÃŃ
    -0.07
    534
    -0.06
    anny
    -0.06
    ÃŃt
    -0.06
     |:
    -0.06
    rane
    -0.06
    stant
    -0.06
    کز
    -0.06
    bes
    -0.06
    odesk
    -0.06
    POSITIVE LOGITS
    itta
    0.07
    owie
    0.06
     Done
    0.06
    Ø°ÙĬ
    0.06
    .TestCase
    0.06
    Done
    0.06
     putas
    0.06
    меÑĩ
    0.06
    бав
    0.06
    ertools
    0.06
    Activations Density 0.018%

    No Known Activations