© 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 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. 85314
    Prev
    Next
    INDEX
    Explanations

    logistical challenges and competitions

    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
    çªĹ
    -0.07
    afen
    -0.07
    _scope
    -0.07
    æ£ĭ
    -0.06
    .study
    -0.06
    agma
    -0.06
    cie
    -0.06
    askell
    -0.06
     BASIS
    -0.06
    inned
    -0.06
    POSITIVE LOGITS
     obstacles
    0.08
     obstacle
    0.08
    PackageName
    0.07
    _challenge
    0.07
    pit
    0.07
     challenge
    0.07
    omu
    0.07
     Challenge
    0.06
    oug
    0.06
    geist
    0.06
    Activations Density 0.004%

    No Known Activations