© 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. 116825
    Prev
    Next
    INDEX
    Explanations

    references to musical comparisons or adaptations

    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
    ople
    -0.07
    ãģĸ
    -0.06
    tesy
    -0.05
     following
    -0.05
    han
    -0.05
    æ§
    -0.05
     Hollow
    -0.05
    è¬Ŀ
    -0.05
     chu
    -0.05
     hollow
    -0.05
    POSITIVE LOGITS
     original
    0.28
     originals
    0.27
    original
    0.26
     оÑĢиг
    0.21
    Original
    0.21
    -original
    0.21
    _original
    0.21
     Original
    0.21
     ORIGINAL
    0.21
    /original
    0.20
    Activations Density 0.052%

    No Known Activations