© 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. 18423
    Prev
    Next
    INDEX
    Explanations

    instructions or usage details for functional devices or systems

    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
    tabpanel
    -0.08
    alin
    -0.07
    Scoped
    -0.07
    rana
    -0.07
    iten
    -0.07
    ansa
    -0.07
    SCO
    -0.07
    iring
    -0.07
    erne
    -0.07
     jsonResponse
    -0.07
    POSITIVE LOGITS
     machines
    0.08
     machine
    0.07
     autom
    0.07
     automatically
    0.07
     software
    0.07
     computers
    0.07
     computer
    0.06
    -machine
    0.06
    your
    0.06
     system
    0.06
    Activations Density 0.050%

    No Known Activations