© 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. 17-LLAMASCOPE-RES-131K
    11. 78180
    Prev
    Next
    INDEX
    Explanations

    terms related to wireless sensor networks and their performance metrics

    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
    teg
    -0.07
     Fet
    -0.07
     Kub
    -0.06
    iete
    -0.06
    RowCount
    -0.06
     train
    -0.06
    ibar
    -0.06
    ooled
    -0.06
    lag
    -0.06
    oice
    -0.06
    POSITIVE LOGITS
     Formation
    0.08
    hop
    0.08
    -network
    0.07
     formation
    0.07
    -hop
    0.07
    _overlay
    0.07
     formations
    0.07
    formed
    0.07
    å½¢æĪIJ
    0.07
    ijkstra
    0.07
    Activations Density 0.037%

    No Known Activations