© 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. 84409
    Prev
    Next
    INDEX
    Explanations

    specific cosmic entities and their related emissions

    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
     Kansas
    -0.07
    emet
    -0.07
    ertino
    -0.06
    ouri
    -0.06
    ampo
    -0.06
     Fay
    -0.06
    ILE
    -0.06
    ختÙĩ
    -0.06
     ä¹
    -0.06
    idor
    -0.06
    POSITIVE LOGITS
     magnet
    0.08
     puls
    0.08
    ç£ģ
    0.08
     Magnet
    0.07
    cca
    0.07
     Pace
    0.07
    .ServiceModel
    0.07
    iron
    0.07
    chez
    0.07
    atron
    0.07
    Activations Density 0.020%

    No Known Activations