© 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. 82893
    Prev
    Next
    INDEX
    Explanations

    code or commands related to project build processes

    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
     Binder
    -0.07
    angu
    -0.07
    loor
    -0.06
    ORK
    -0.06
    aoke
    -0.06
    ranking
    -0.06
    _BIND
    -0.06
    yny
    -0.06
    assignments
    -0.06
     Rust
    -0.06
    POSITIVE LOGITS
    еÑĦ
    0.07
    547
    0.07
    ãĥ©ãĤ¤ãĥ³
    0.06
    CDATA
    0.06
    .xml
    0.06
    .XML
    0.06
     اÙĦرÙħزÙĬØ©
    0.06
     BUILD
    0.06
     osg
    0.06
    /DTD
    0.06
    Activations Density 0.014%

    No Known Activations