© 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. 17-LLAMASCOPE-RES-131K
    11. 93944
    Prev
    Next
    INDEX
    Explanations

    phrases indicating exposure to various risks or environmental factors

    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
     ÑĥÑĩаÑģÑĤÑĮ
    -0.06
    Accessor
    -0.06
     tức
    -0.06
     provision
    -0.06
    à¤ķन
    -0.06
    "."
    -0.06
     appearance
    -0.06
     appearances
    -0.06
    dden
    -0.06
     Perr
    -0.06
    POSITIVE LOGITS
     environments
    0.07
     sights
    0.07
     scrutiny
    0.07
    umba
    0.07
     dziew
    0.06
    lings
    0.06
    ieve
    0.06
     exposure
    0.06
     risks
    0.06
    .icons
    0.06
    Activations Density 0.015%

    No Known Activations