© 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. 121028
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to licensing and permits

    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
    ums
    -0.06
    acons
    -0.06
     legally
    -0.06
    immer
    -0.06
    egers
    -0.06
    isku
    -0.06
    eds
    -0.06
     окон
    -0.06
    arto
    -0.05
    inker
    -0.05
    POSITIVE LOGITS
    /lic
    0.09
    /LICENSE
    0.07
    ream
    0.07
    tl
    0.07
    /license
    0.07
    wed
    0.07
    ipt
    0.06
    OLER
    0.06
     reusable
    0.06
     TL
    0.06
    Activations Density 0.005%

    No Known Activations