© 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. 93837
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to leveraging resources or capabilities

    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
     Pazar
    -0.08
    /Dk
    -0.07
     porr
    -0.07
    áºł
    -0.07
    ulary
    -0.07
    thur
    -0.07
    continent
    -0.07
    ubo
    -0.07
    รà¸Ķ
    -0.07
    aram
    -0.07
    POSITIVE LOGITS
     resources
    0.07
    675
    0.07
     existing
    0.07
     opportunities
    0.07
    581
    0.07
     Coat
    0.07
     Existing
    0.06
    947
    0.06
     leverage
    0.06
     expertise
    0.06
    Activations Density 0.005%

    No Known Activations