© 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. 2880
    Prev
    Next
    INDEX
    Explanations

    references to interactive content such as images or clickable links

    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
    atten
    -0.06
    ieee
    -0.06
     recording
    -0.06
    ocket
    -0.06
    наÑĢ
    -0.06
    ISION
    -0.06
    acock
    -0.06
     Recording
    -0.06
    dfs
    -0.06
    лÑĥÑĩ
    -0.06
    POSITIVE LOGITS
     sizing
    0.08
    ksam
    0.07
    .Stretch
    0.07
     size
    0.07
     siz
    0.07
    -sizing
    0.07
     ÑĢазмеÑĢ
    0.07
     Obs
    0.07
    <source
    0.06
    ulings
    0.06
    Activations Density 0.006%

    No Known Activations