© 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. 15-LLAMASCOPE-RES-131K
    11. 90153
    Prev
    Next
    INDEX
    Explanations

    references to traditional meal components

    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
    миÑĢ
    -0.06
    å¯
    -0.06
    filer
    -0.06
     EITHER
    -0.06
     (%)
    -0.06
    ãģłãģijãģ§
    -0.05
    оÑĥ
    -0.05
    عات
    -0.05
    ê°ĢìļĶ
    -0.05
    olt
    -0.05
    POSITIVE LOGITS
    elere
    0.08
     ogs
    0.07
    åĨµ
    0.07
    ë¦Ħ
    0.07
    assen
    0.07
    eler
    0.07
    éli
    0.07
    hatt
    0.07
    udget
    0.07
     copyrighted
    0.06
    Activations Density 0.005%

    No Known Activations