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

    Neuronpedia

    Jacobian LensNEW
    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. 17-LLAMASCOPE-RES-131K
    11. 131067
    Prev
    Next
    INDEX
    Explanations

    syntactical structures and programmatic elements related to coding and development of applications

    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
    )↵
    -0.06
     ...)↵
    -0.06
    acl
    -0.06
     --------↵
    -0.06
     âĨĴ↵↵
    -0.06
    olini
    -0.06
    ;↵
    -0.06
    ECTOR
    -0.06
    atoes
    -0.06
    ade
    -0.06
    POSITIVE LOGITS
    auer
    0.08
     âĢ¢
    0.08
     aalborg
    0.08
     (“
    0.07
    ruz
    0.07
    olik
    0.07
     ![
    0.07
     ·
    0.07
    ±Ð¾ÑĤ
    0.07
      ↵  ↵
    0.07
    Activations Density 0.333%

    No Known Activations