© 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. 17-LLAMASCOPE-RES-131K
    11. 119541
    Prev
    Next
    INDEX
    Explanations

    elements related to comfort and fit for wearable technology

    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
     Levine
    -0.06
    BIN
    -0.06
     Arb
    -0.06
     Emerging
    -0.06
     Broken
    -0.06
    arkin
    -0.06
     Simmons
    -0.05
     newsletter
    -0.05
     Imm
    -0.05
    /tests
    -0.05
    POSITIVE LOGITS
    .scalablytyped
    0.08
    icht
    0.07
    chwitz
    0.07
    SKTOP
    0.07
    cheiden
    0.07
    owler
    0.07
    chet
    0.06
    ClickListener
    0.06
    oose
    0.06
    ROLLER
    0.06
    Activations Density 0.049%

    No Known Activations