© 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. 81161
    Prev
    Next
    INDEX
    Explanations

    references to actions, conditions, and events related to experiences and progress

    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
     almost
    -0.09
    almost
    -0.07
    anguage
    -0.07
    arges
    -0.07
     Aut
    -0.07
    alth
    -0.07
     just
    -0.07
    ancel
    -0.07
     least
    -0.06
    ëĿ¼ëıĦ
    -0.06
    POSITIVE LOGITS
     à¤ĩतन
    0.07
    imus
    0.07
    ODB
    0.07
    _ONCE
    0.07
    UCCEEDED
    0.07
    ularity
    0.07
    sofar
    0.07
     лиÑĪÑĮ
    0.07
    fans
    0.07
    ay
    0.07
    Activations Density 0.091%

    No Known Activations