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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 95669
    Prev
    Next
    INDEX
    Explanations

    terms related to patient care and positioning techniques

    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
    amps
    -0.07
    ãĥ¼ãĤ
    -0.06
     BIN
    -0.06
    ück
    -0.06
    nost
    -0.06
     ages
    -0.05
    sher
    -0.05
    l
    -0.05
    esson
    -0.05
     Marketplace
    -0.05
    POSITIVE LOGITS
     Bur
    0.07
     bur
    0.07
    pci
    0.06
     киÑĪ
    0.06
    воÑİ
    0.06
     Eigen
    0.06
    åłĤ
    0.06
    ValueChanged
    0.06
    osten
    0.06
    hoa
    0.06
    Activations Density 0.016%

    No Known Activations