© 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. 105414
    Prev
    Next
    INDEX
    Explanations

    references to endorsements or testimonials related to a product or service

    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
    pi
    -0.07
    953
    -0.06
     Dak
    -0.06
    529
    -0.06
     Pike
    -0.06
    :UIAlert
    -0.06
     Pi
    -0.06
    53
    -0.06
    799
    -0.06
    ent
    -0.05
    POSITIVE LOGITS
    plib
    0.08
    طر
    0.08
    _TRIANGLE
    0.08
    .kr
    0.07
    ernaut
    0.07
    /extensions
    0.07
    аÑĢÑĮ
    0.07
    emento
    0.07
    interop
    0.07
    untime
    0.06
    Activations Density 0.003%

    No Known Activations