© 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 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. 88458
    Prev
    Next
    INDEX
    Explanations

    themes related to saving or protecting a community or environment

    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
    ertools
    -0.07
    اØ
    -0.07
    603
    -0.07
    PFN
    -0.07
    _literals
    -0.06
    åĪº
    -0.06
     depart
    -0.06
    üf
    -0.06
    066
    -0.06
    accumulate
    -0.06
    POSITIVE LOGITS
     innoc
    0.07
     innocent
    0.07
    _IOCTL
    0.07
    ellen
    0.06
     Jord
    0.06
    /save
    0.06
     entire
    0.06
     himself
    0.06
    ptune
    0.06
    contre
    0.06
    Activations Density 0.012%

    No Known Activations