© 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. 106366
    Prev
    Next
    INDEX
    Explanations

    programming-related constructs and error handling specifications 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
    -Methods
    -0.07
    oster
    -0.06
    afia
    -0.06
    ãĤīãģı
    -0.06
    UTDOWN
    -0.06
     UITableViewController
    -0.06
     Mississippi
    -0.06
    ilmington
    -0.06
     Tamil
    -0.06
    Tower
    -0.06
    POSITIVE LOGITS
     Newport
    0.08
    .scalablytyped
    0.08
     Kral
    0.08
    ustria
    0.06
    kubectl
    0.06
    avl
    0.06
    asia
    0.06
    YD
    0.06
    .MixedReality
    0.06
    Unhandled
    0.06
    Activations Density 0.004%

    No Known Activations