© 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 EvalsExportsinterp-engineNEWAPI 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. 27907
    Prev
    Next
    INDEX
    Explanations

    instances of complex relationships or contrasts

    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
    /renderer
    -0.07
     HOWEVER
    -0.07
    ought
    -0.07
    kün
    -0.07
    ï¼ĸ
    -0.07
    onte
    -0.07
    ILT
    -0.06
     breat
    -0.06
    ï¼Ļ
    -0.06
    EI
    -0.06
    POSITIVE LOGITS
     definitely
    0.07
     certainly
    0.06
     specifically
    0.06
     just
    0.06
     necessarily
    0.06
     enough
    0.06
    719
    0.06
    lify
    0.06
     âĹĦ
    0.05
    ertain
    0.05
    Activations Density 0.017%

    No Known Activations