© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 106796
    Prev
    Next
    INDEX
    Explanations

    references to "node" in a technical context, likely related to programming or data structures

    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
    ners
    -0.07
    agna
    -0.07
    subtotal
    -0.07
    orca
    -0.07
    rors
    -0.07
    thesis
    -0.07
    pedo
    -0.07
    λιά
    -0.07
    sembles
    -0.07
    rub
    -0.07
    POSITIVE LOGITS
    isch
    0.08
     desn
    0.08
    _modules
    0.07
    azon
    0.06
    FAULT
    0.06
     Bare
    0.06
    lete
    0.06
     Pron
    0.06
    fault
    0.06
    ahr
    0.05
    Activations Density 0.003%

    No Known Activations