© 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. 4666
    Prev
    Next
    INDEX
    Explanations

    conditions and guidelines related to health and safety protocols

    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
    ockey
    -0.07
    CLU
    -0.07
     kvin
    -0.06
    Barrier
    -0.06
     dig
    -0.06
     éĩİ
    -0.06
    pointer
    -0.06
    ิสà¸ķ
    -0.06
    ipa
    -0.06
    nock
    -0.06
    POSITIVE LOGITS
    å¯Į
    0.07
     Bench
    0.06
     wealthy
    0.06
     nearby
    0.06
    Ñĩе
    0.06
     benchmarks
    0.06
    availability
    0.06
    ÑĢел
    0.06
    ximity
    0.06
     availability
    0.06
    Activations Density 0.063%

    No Known Activations