© 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. 22-LLAMASCOPE-RES-131K
    11. 3933
    Prev
    Next
    INDEX
    Explanations

    verb forms and their variations related to status and existence

    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
    omez
    -0.08
    aka
    -0.08
    à¸ļà¸Ĺ
    -0.08
    asc
    -0.08
    idla
    -0.08
    folio
    -0.07
    ovice
    -0.07
    abbr
    -0.07
    arend
    -0.07
    orge
    -0.07
    POSITIVE LOGITS
     mum
    0.08
     already
    0.08
     final
    0.08
     on
    0.07
     currently
    0.07
     serious
    0.07
     planning
    0.07
     now
    0.07
     all
    0.07
     at
    0.07
    Activations Density 0.037%

    No Known Activations