© 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. 106307
    Prev
    Next
    INDEX
    Explanations

    concepts related to access and opportunities in education and community support

    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
     Wass
    -0.06
     Bald
    -0.06
    rox
    -0.06
    cean
    -0.06
    QRS
    -0.06
    ulumi
    -0.06
     comprom
    -0.06
     plu
    -0.06
    aklı
    -0.06
     convention
    -0.06
    POSITIVE LOGITS
     services
    0.09
     kepada
    0.08
     guidance
    0.08
     opportunities
    0.07
    services
    0.07
     opportunity
    0.07
     insight
    0.07
    _services
    0.07
    Services
    0.07
     insights
    0.07
    Activations Density 0.173%

    No Known Activations