© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 4087
    Prev
    Next
    INDEX
    Explanations

    dates and locations related to academic or professional events

    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
    wand
    -0.08
    iaux
    -0.08
    ibling
    -0.08
    nowrap
    -0.07
    lesh
    -0.07
    еÑĤа
    -0.07
    icont
    -0.07
    нож
    -0.07
    etta
    -0.07
    alsa
    -0.06
    POSITIVE LOGITS
    æĪIJ
    0.07
    UV
    0.06
     held
    0.06
    held
    0.06
     UV
    0.06
     hosted
    0.06
    maal
    0.06
    ypi
    0.05
     bri
    0.05
     quoted
    0.05
    Activations Density 0.021%

    No Known Activations