© 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. 4735
    Prev
    Next
    INDEX
    Explanations

    references to taxation and legal frameworks

    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
    ouri
    -0.06
    vak
    -0.06
    umn
    -0.06
    scriptId
    -0.05
    åĩºçļĦ
    -0.05
    isch
    -0.05
    çķª
    -0.05
    trial
    -0.05
    âĢ¦↵
    -0.05
     realization
    -0.05
    POSITIVE LOGITS
     system
    0.08
     Act
    0.08
    ogo
    0.07
    اÙĨس
    0.07
    cheme
    0.07
    ød
    0.07
     ActionTypes
    0.07
    HttpException
    0.07
     TMPro
    0.07
    Ø®ÙĪ
    0.07
    Activations Density 0.047%

    No Known Activations