Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 82807
    Prev
    Next
    INDEX
    Explanations

    Java method and variable declarations in programming code

    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
    IODevice
    -0.06
     deriv
    -0.06
    licer
    -0.06
     zav
    -0.06
    šli
    -0.06
    WRAPPER
    -0.06
    .Binding
    -0.06
    (("
    -0.06
     vess
    -0.06
    POSITIVE LOGITS
    odox
    0.07
    еж
    0.06
    iotic
    0.06
    uelle
    0.06
    gaard
    0.06
    alla
    0.06
    oxic
    0.06
     =
    0.06
    imeType
    0.06
    eries
    0.06
    Activations Density 0.005%

    No Known Activations