© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 5-LLAMASCOPE-RES-131K
    11. 125404
    Prev
    Next
    INDEX
    Explanations

    terms related to medical conditions and protein levels in a clinical context

    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
    cntl
    -0.07
    elt
    -0.07
    ught
    -0.07
    æĬ¼
    -0.07
     неÑģп
    -0.07
    åĬ
    -0.07
    ActivityResult
    -0.07
    ãĤ·ãĥ¼
    -0.07
    onium
    -0.07
    ão
    -0.07
    POSITIVE LOGITS
     Ain
    0.06
     restricted
    0.06
     Drops
    0.06
    uria
    0.06
    omed
    0.06
    IEW
    0.06
     Dro
    0.06
    ARIO
    0.06
    ks
    0.05
     limited
    0.05
    Activations Density 0.006%

    No Known Activations