© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 74449
    Prev
    Next
    INDEX
    Explanations

    terms related to connectivity and communication issues

    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
     transitional
    -0.07
    elm
    -0.07
    ahr
    -0.06
     íĨµíķ©
    -0.06
     adul
    -0.06
     dripping
    -0.06
    antt
    -0.06
    æľºåľº
    -0.06
     Pavel
    -0.06
    λιά
    -0.06
    POSITIVE LOGITS
    fiber
    0.09
     Fiber
    0.08
     fiber
    0.08
     cable
    0.08
    æķ·
    0.08
     cables
    0.08
     Cable
    0.07
     Pose
    0.07
    odem
    0.07
     fibre
    0.07
    Activations Density 0.001%

    No Known Activations