© 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. 85474
    Prev
    Next
    INDEX
    Explanations

    activities and processes related to cleaning and removing waste

    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
    ÙĬتÙĬ
    -0.07
    loi
    -0.07
    ursal
    -0.07
    odus
    -0.07
    anten
    -0.07
    .Framework
    -0.07
    èĮĥ
    -0.07
    دÙĪد
    -0.07
    odied
    -0.07
    vÄĽt
    -0.07
    POSITIVE LOGITS
    _bridge
    0.06
    uem
    0.06
    AtPath
    0.06
    gm
    0.06
    825
    0.06
     stre
    0.06
     Crystal
    0.06
     presence
    0.05
     Presence
    0.05
    osl
    0.05
    Activations Density 0.004%

    No Known Activations