© 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. 117993
    Prev
    Next
    INDEX
    Explanations

    structural elements related to formatting and alignment in text

    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
    aub
    -0.07
    -provider
    -0.07
    İ·
    -0.06
    è¼Ŀ
    -0.06
    .unbind
    -0.06
    ÙĦÙħÙĩ
    -0.06
    glomer
    -0.06
    صاÙĦ
    -0.06
    pike
    -0.06
    pickle
    -0.06
    POSITIVE LOGITS
    _indent
    0.08
    (indent
    0.08
     indent
    0.08
     indentation
    0.08
    ullet
    0.07
    .indent
    0.07
    -indent
    0.07
    indent
    0.07
    Indent
    0.07
     line
    0.07
    Activations Density 0.018%

    No Known Activations