Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 44406
    Prev
    Next
    INDEX
    Explanations

    terms related to sailing and marine mechanics

    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
    _qos
    -0.07
     pisc
    -0.06
     aquarium
    -0.06
    cov
    -0.06
    æ»
    -0.06
    .Future
    -0.06
    itre
    -0.06
    ibraltar
    -0.06
     Aquarium
    -0.06
     Fisher
    -0.06
    POSITIVE LOGITS
     trimming
    0.12
     trim
    0.12
     sheet
    0.11
     trimmed
    0.11
     helm
    0.11
     sheets
    0.11
     gy
    0.10
     Trim
    0.10
    trimmed
    0.10
    trim
    0.10
    Activations Density 0.006%

    No Known Activations