© 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. 119256
    Prev
    Next
    INDEX
    Explanations

    specific models and details of cars, particularly convertibles

    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
    vanced
    -0.06
    yk
    -0.06
    EDI
    -0.06
     تÙĤد
    -0.06
    ea
    -0.06
    eam
    -0.06
     Landing
    -0.06
     gou
    -0.06
    aims
    -0.06
     Pod
    -0.06
    POSITIVE LOGITS
     summer
    0.08
     weather
    0.08
     sun
    0.08
    å¤ı
    0.07
    izik
    0.07
     Suns
    0.07
    987
    0.07
     wind
    0.07
    summer
    0.07
     wnd
    0.07
    Activations Density 0.010%

    No Known Activations