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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 681
    Prev
    Next
    INDEX
    Explanations

    terms related to designs and configurations in constructions and 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
    ullo
    -0.08
    ryn
    -0.07
    .mixin
    -0.07
    PropTypes
    -0.07
    dens
    -0.07
    .Ordinal
    -0.07
    Ñĥда
    -0.06
    itler
    -0.06
    /moment
    -0.06
     Www
    -0.06
    POSITIVE LOGITS
     structure
    0.07
     layout
    0.07
    0.07
     Layout
    0.06
     design
    0.06
    ter
    0.06
    /design
    0.06
    åĽ³
    0.06
    /format
    0.06
    TURE
    0.06
    Activations Density 0.053%

    No Known Activations