© 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. 1702
    Prev
    Next
    INDEX
    Explanations

    references to a sense of resolution or conclusion

    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
     ↵↵
    -0.08
     Handy
    -0.07
    енÑĤÑĥ
    -0.07
     sudden
    -0.07
    "';
    -0.07
    ons
    -0.07
    edly
    -0.06
    ABI
    -0.06
    rior
    -0.06
    rey
    -0.06
    POSITIVE LOGITS
     (?)
    0.08
    -ÑĤаки
    0.07
    yyyy
    0.07
    /current
    0.07
    íģ¼
    0.07
    Å¡ek
    0.07
    mente
    0.06
    AYOUT
    0.06
    succ
    0.06
    /full
    0.06
    Activations Density 0.014%

    No Known Activations