© 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. 85470
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords, particularly those dealing with application and method definitions

    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
     foot
    -0.06
    aldo
    -0.06
    dw
    -0.06
    ffic
    -0.06
    thon
    -0.06
    rak
    -0.06
    _INTR
    -0.05
     Hast
    -0.05
    rita
    -0.05
    STM
    -0.05
    POSITIVE LOGITS
     appName
    0.07
     runApp
    0.07
    ovna
    0.07
    .application
    0.07
    lict
    0.07
     launch
    0.07
    _ground
    0.06
     EntryPoint
    0.06
    å±ĭ
    0.06
    orum
    0.06
    Activations Density 0.000%

    No Known Activations