© 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. 15-LLAMASCOPE-RES-131K
    11. 103364
    Prev
    Next
    INDEX
    Explanations

    technical terms related to programming and software management

    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
    ati
    -0.07
    =input
    -0.06
     Latter
    -0.06
     stran
    -0.06
    ÄĻż
    -0.06
     Manning
    -0.06
    ır
    -0.06
    æĿ
    -0.06
    eker
    -0.06
    é¾į
    -0.06
    POSITIVE LOGITS
    iras
    0.07
    imet
    0.06
    åĵģ
    0.06
    än
    0.06
    驶
    0.06
    neau
    0.06
    iani
    0.06
    ondo
    0.06
     whisk
    0.06
    uma
    0.06
    Activations Density 0.001%

    No Known Activations