© 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. 75537
    Prev
    Next
    INDEX
    Explanations

    structural elements of texts and their classifications

    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
     McGu
    -0.07
     besten
    -0.06
    RSS
    -0.06
    atorium
    -0.06
    .sid
    -0.06
    _minimum
    -0.06
    _pb
    -0.06
    Combine
    -0.06
    .dtd
    -0.06
    aires
    -0.06
    POSITIVE LOGITS
    Ưá»
    0.08
    ofs
    0.07
     miscellaneous
    0.07
     prelim
    0.06
    lude
    0.06
    jest
    0.06
    angen
    0.06
     nuts
    0.06
    ages
    0.06
    indy
    0.06
    Activations Density 0.013%

    No Known Activations