© 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. 61694
    Prev
    Next
    INDEX
    Explanations

    references to literary translations and notable publications

    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
     sp
    -0.06
     scientific
    -0.06
    -0.06
     canyon
    -0.06
    ı
    -0.05
     stuff
    -0.05
    chter
    -0.05
    sequential
    -0.05
     ext
    -0.05
    tat
    -0.05
    POSITIVE LOGITS
    ecko
    0.08
    _RESOURCES
    0.07
     Cursors
    0.07
    ÏĢε
    0.07
     Matchers
    0.07
    .struts
    0.07
     ÙĥÙĨت
    0.07
    ëŀ«
    0.07
    _https
    0.07
    .byId
    0.07
    Activations Density 0.005%

    No Known Activations