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

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 61437
    Prev
    Next
    INDEX
    Explanations

    conditional statements regarding medical symptoms and their responses

    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
    hn
    -0.06
    rete
    -0.06
    Tau
    -0.06
     Lat
    -0.06
    innen
    -0.06
    ære
    -0.06
     sir
    -0.06
    Ã
    -0.05
     key
    -0.05
     relocate
    -0.05
    POSITIVE LOGITS
    arb
    0.08
    è¿ĺæĺ¯
    0.07
    elerik
    0.07
    .generated
    0.07
     continued
    0.07
    çļĦæĥħåĨµ
    0.07
    γκα
    0.07
    eÅŁ
    0.07
    arra
    0.07
    _serializer
    0.07
    Activations Density 0.011%

    No Known Activations