© 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. 106936
    Prev
    Next
    INDEX
    Explanations

    connections and relationships among academic institutions and societal issues

    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
    umd
    -0.08
    ulings
    -0.07
    _mA
    -0.07
    chine
    -0.07
    ĨĴ
    -0.07
    ãĥ³ãĥij
    -0.06
    egot
    -0.06
    roupon
    -0.06
    tıģ
    -0.06
    reate
    -0.06
    POSITIVE LOGITS
     future
    0.31
    future
    0.27
     Future
    0.24
    Future
    0.23
    æľªæĿ¥
    0.21
     futuro
    0.21
     бÑĥдÑĥÑī
    0.20
     tomorrow
    0.18
     fut
    0.18
    _future
    0.18
    Activations Density 0.075%

    No Known Activations