© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 103539
    Prev
    Next
    INDEX
    Explanations

    content related to digital devices and wallpapers

    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
    idos
    -0.08
    oud
    -0.06
    ContentLoaded
    -0.06
    igel
    -0.06
     Paz
    -0.06
    angel
    -0.06
    icast
    -0.06
    anges
    -0.05
    onte
    -0.05
    atoire
    -0.05
    POSITIVE LOGITS
    anca
    0.08
     purposes
    0.07
    638
    0.07
    maj
    0.07
    ä»ķ
    0.06
    _Thread
    0.06
    YS
    0.06
     CONSEQUENTIAL
    0.06
    .Selenium
    0.06
    ollo
    0.06
    Activations Density 0.004%

    No Known Activations