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

    Neuronpedia

    Jacobian LensNEW
    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. 17-LLAMASCOPE-RES-131K
    11. 88352
    Prev
    Next
    INDEX
    Explanations

    instances of community or population references

    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
    isted
    -0.06
    ubes
    -0.06
     Went
    -0.06
     Piper
    -0.06
    heits
    -0.05
    .AI
    -0.05
     Hos
    -0.05
     Bear
    -0.05
    ÃŃ
    -0.05
    bons
    -0.05
    POSITIVE LOGITS
     ÐĿаÑģеление
    0.09
     population
    0.08
    population
    0.08
    اÛĮت
    0.08
    alink
    0.08
    íĢ
    0.08
    deen
    0.07
     ÙħساØŃت
    0.07
    innie
    0.07
    ITLE
    0.07
    Activations Density 0.003%

    No Known Activations