© 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. 39371
    Prev
    Next
    INDEX
    Explanations

    elements and components related to recreational activities and outdoor adventures

    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
    zcze
    -0.06
    ptune
    -0.06
    åĨĨ
    -0.06
    ueva
    -0.06
    ultip
    -0.06
    fore
    -0.06
    eniable
    -0.06
    lags
    -0.06
    wart
    -0.06
    ipur
    -0.06
    POSITIVE LOGITS
     Airways
    0.09
     flight
    0.09
     airspace
    0.09
     flights
    0.08
     Flight
    0.08
     flyers
    0.08
    Flight
    0.07
     Flyers
    0.07
     flying
    0.07
    翼
    0.07
    Activations Density 0.006%

    No Known Activations