© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 76389
    Prev
    Next
    INDEX
    Explanations

    programming-related identifiers and comments in 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
    onica
    -0.10
    ttp
    -0.09
    hsi
    -0.08
    oÅĻ
    -0.07
     ConfigureServices
    -0.07
    .mdl
    -0.07
    ylie
    -0.07
    onse
    -0.07
     ÙħÙĨÙĩا
    -0.07
    iá»ģm
    -0.07
    POSITIVE LOGITS
    ero
    0.07
    _FLUSH
    0.06
    ccoli
    0.06
    eros
    0.06
    entr
    0.05
     sag
    0.05
    nic
    0.05
     Commons
    0.05
     Gim
    0.05
    ục
    0.05
    Activations Density 0.002%

    No Known Activations