© 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. 119253
    Prev
    Next
    INDEX
    Explanations

    scientific concepts related to dark matter and its properties

    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
    urum
    -0.07
    ADE
    -0.06
    dete
    -0.06
     âĹĦ
    -0.06
     Shut
    -0.06
    _verbose
    -0.06
    ottom
    -0.06
    /locale
    -0.06
    ;element
    -0.06
     cent
    -0.06
    POSITIVE LOGITS
     properties
    0.09
     Properties
    0.08
    properties
    0.08
     Attributes
    0.07
    attributes
    0.07
    'gc
    0.07
    ardi
    0.07
    ©
    0.06
    652
    0.06
    ì§ĵ
    0.06
    Activations Density 0.067%

    No Known Activations