© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 84974
    Prev
    Next
    INDEX
    Explanations

    code syntax related to object-oriented programming in a specific language

    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
    nodeValue
    -0.07
    hud
    -0.07
    esan
    -0.07
    {}.
    -0.06
    getChild
    -0.06
    utes
    -0.06
    gne
    -0.06
    axed
    -0.06
    862
    -0.06
    icism
    -0.06
    POSITIVE LOGITS
     private
    0.07
     Hers
    0.06
     Plantae
    0.06
    untime
    0.06
    ledge
    0.06
     situ
    0.06
     Gardens
    0.06
    jÃŃ
    0.06
     _
    0.06
    ounty
    0.06
    Activations Density 0.004%

    No Known Activations