© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 83756
    Prev
    Next
    INDEX
    Explanations

    mentions of support or assistance to individuals or groups in need

    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
    irket
    -0.08
    ogui
    -0.07
    ogue
    -0.07
    สà¸Ļ
    -0.07
    ationale
    -0.07
    niž
    -0.07
    аÑĤег
    -0.07
    arResult
    -0.07
    ÏĥÏĢ
    -0.07
     nuôi
    -0.07
    POSITIVE LOGITS
     us
    0.08
    fully
    0.08
     efforts
    0.07
    lessly
    0.07
     unders
    0.07
     towards
    0.07
    å¿Ļ
    0.07
    .epam
    0.06
     toward
    0.06
     effort
    0.06
    Activations Density 0.017%

    No Known Activations