© 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. 130544
    Prev
    Next
    INDEX
    Explanations

    references to theoretical physics models and frameworks

    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
    allo
    -0.06
    stad
    -0.06
    amo
    -0.06
    åºĬ
    -0.06
    oku
    -0.06
    ogo
    -0.06
    ayout
    -0.06
    endo
    -0.06
    âĢ¦↵
    -0.06
     Spielberg
    -0.06
    POSITIVE LOGITS
     dÄ±ÅŁÄ±
    0.07
    åıĬåħ¶
    0.07
    bench
    0.07
    wide
    0.07
     доп
    0.07
    adden
    0.07
    -Compatible
    0.07
    овеÑĢ
    0.07
    _COMPAT
    0.06
     JPG
    0.06
    Activations Density 0.018%

    No Known Activations