© 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. 73596
    Prev
    Next
    INDEX
    Explanations

    phrases indicating relationships or conditions of equivalence

    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
    asser
    -0.07
     sake
    -0.07
    ZA
    -0.07
    plemented
    -0.06
    ippi
    -0.06
    ien
    -0.06
    asha
    -0.06
    κε
    -0.06
    MX
    -0.06
    Say
    -0.06
    POSITIVE LOGITS
     rằng
    0.17
     that
    0.16
     bahwa
    0.14
     ÙĪØ£ÙĨ
    0.14
    that
    0.14
    	that
    0.11
     ÏĮÏĦι
    0.11
     że
    0.10
     že
    0.10
     että
    0.10
    Activations Density 0.078%

    No Known Activations