© 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. 1942
    Prev
    Next
    INDEX
    Explanations

    phrases related to outdoor activities and adventure

    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
    wj
    -0.06
     Rosenstein
    -0.06
    rika
    -0.06
    .hl
    -0.06
    ekli
    -0.06
    _fk
    -0.06
    quan
    -0.06
     prompts
    -0.06
     behalf
    -0.06
     Jak
    -0.06
    POSITIVE LOGITS
     Serialization
    0.06
    abor
    0.06
    otec
    0.06
    anton
    0.06
     shaved
    0.06
    adow
    0.06
    imoto
    0.06
    aÄį
    0.06
     Tyson
    0.06
    æĹ¥
    0.06
    Activations Density 0.005%

    No Known Activations