© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 2972
    Prev
    Next
    INDEX
    Explanations

    content related to outdoor activities and nature exploration

    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
    .SaveChangesAsync
    -0.07
    orgot
    -0.07
    .openg
    -0.06
     mountains
    -0.06
    folk
    -0.06
     downhill
    -0.06
    duct
    -0.06
    cin
    -0.06
    ortal
    -0.06
    æ¡£
    -0.06
    POSITIVE LOGITS
     path
    0.09
     paths
    0.09
     loop
    0.09
     Paths
    0.09
    .walk
    0.08
     walking
    0.08
     walks
    0.08
    <path
    0.08
     walk
    0.08
     yürüy
    0.08
    Activations Density 0.011%

    No Known Activations