© 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. 41244
    Prev
    Next
    INDEX
    Explanations

    the letter "s" used as a standalone character or in various contexts

    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
    evice
    -0.07
    .mj
    -0.07
    haps
    -0.07
    UG
    -0.07
    robat
    -0.06
    ledo
    -0.06
    êµIJíļĮ
    -0.06
     vej
    -0.06
    orget
    -0.06
     باش
    -0.06
    POSITIVE LOGITS
    ERRQ
    0.07
     âĨIJ
    0.06
     Peace
    0.06
    _cpp
    0.06
     peace
    0.06
     ï¼ļ
    0.05
    _DH
    0.05
    æĸ½
    0.05
    ÙĬرÙĬ
    0.05
     Ø¢ÙĦ
    0.05
    Activations Density 0.249%

    No Known Activations