© 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. 54976
    Prev
    Next
    INDEX
    Explanations

    comparative statements about probiotic products

    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
    ectl
    -0.08
     Overrides
    -0.07
    ught
    -0.06
    è¸
    -0.06
    ombat
    -0.06
    /releases
    -0.06
    udu
    -0.06
    .biz
    -0.06
    bcd
    -0.06
    æĪ
    -0.06
    POSITIVE LOGITS
     ÙĪاب
    0.06
    iaux
    0.06
    ียà¸ĩ
    0.06
    æł¹æľ¬
    0.06
    ActionCreators
    0.06
     ValueEventListener
    0.06
     Antar
    0.06
    æ¶
    0.06
    insic
    0.06
     Leer
    0.06
    Activations Density 0.003%

    No Known Activations