© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 85945
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to radical proposals and changes

    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
    aggi
    -0.07
    //{{
    -0.07
     Ä°z
    -0.07
    .::
    -0.07
     Ãĸzel
    -0.07
    Interop
    -0.07
     Ãľn
    -0.07
     Sır
    -0.07
    .Formatter
    -0.07
    _DL
    -0.07
    POSITIVE LOGITS
    quam
    0.07
    oliberal
    0.06
    éĽĦ
    0.06
    ody
    0.06
     serialVersionUID
    0.06
    amp
    0.06
     UITableViewCell
    0.05
    ekt
    0.05
    ompiler
    0.05
    epend
    0.05
    Activations Density 0.024%

    No Known Activations