© 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. 84970
    Prev
    Next
    INDEX
    Explanations

    specific markup or structural elements in code or XML

    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
    els
    -0.08
    anh
    -0.07
    riv
    -0.07
    igel
    -0.07
    usiness
    -0.07
     Markus
    -0.07
    olis
    -0.07
    eut
    -0.06
    559
    -0.06
    ihil
    -0.06
    POSITIVE LOGITS
    ãĥ¼ãĥŃ
    0.07
    ãĥ«ãĥī
    0.07
    ounge
    0.07
     Barker
    0.06
     tongues
    0.06
    odos
    0.06
     Jako
    0.06
    rez
    0.06
     POLL
    0.06
    .plugin
    0.05
    Activations Density 0.001%

    No Known Activations