© 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. 17-LLAMASCOPE-RES-131K
    6. 82450
    Prev
    Next
    INDEX
    Explanations

    URLs and script source references in HTML code

    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
     traps
    -0.06
    ót
    -0.06
     trap
    -0.05
     Sens
    -0.05
    ral
    -0.05
    /interfaces
    -0.05
    vat
    -0.05
    aced
    -0.05
    urn
    -0.05
     Janeiro
    -0.05
    POSITIVE LOGITS
    nech
    0.08
    ertino
    0.08
    istring
    0.07
    _sf
    0.07
    quam
    0.07
    unas
    0.07
    ÙĬرا
    0.07
    é³´
    0.07
     halde
    0.07
     PVOID
    0.07
    Activations Density 0.003%

    No Known Activations