© 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. 15-LLAMASCOPE-RES-131K
    11. 88256
    Prev
    Next
    INDEX
    Explanations

    instances of visual observation or witnessing individuals in various contexts

    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
    ãĥ¼ãĥ«
    -0.06
    isz
    -0.06
    tha
    -0.06
    ave
    -0.06
    sher
    -0.06
    çķĻ
    -0.06
    /cs
    -0.06
    leting
    -0.06
    ::__
    -0.06
    æļ®
    -0.06
    POSITIVE LOGITS
    ãģ¹
    0.06
    QA
    0.06
    tems
    0.06
    aska
    0.06
    763
    0.06
    473
    0.06
    tings
    0.06
    kyt
    0.06
    bsp
    0.06
    ÏĥÏĦο
    0.06
    Activations Density 0.008%

    No Known Activations