© 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. 79162
    Prev
    Next
    INDEX
    Explanations

    names of individuals and their associated professional roles or affiliations

    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
    alore
    -0.07
    ya
    -0.07
    .ops
    -0.06
    cie
    -0.06
    ayet
    -0.06
    imenti
    -0.06
     Fur
    -0.06
    thin
    -0.06
    arti
    -0.06
    Äħd
    -0.06
    POSITIVE LOGITS
     Jr
    0.07
    kyt
    0.07
     san
    0.06
    ÏĦο
    0.06
    igy
    0.06
     Hubb
    0.06
     fractional
    0.06
    oice
    0.06
     Beard
    0.06
     thems
    0.06
    Activations Density 0.006%

    No Known Activations