© 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. 129583
    Prev
    Next
    INDEX
    Explanations

    references to historical or academic works and their details

    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
    osti
    -0.07
    aign
    -0.07
    iversal
    -0.06
     âĢª
    -0.06
     schö
    -0.06
    oine
    -0.06
    ToFit
    -0.06
    iddi
    -0.06
    bove
    -0.06
    obre
    -0.06
    POSITIVE LOGITS
    ;element
    0.07
    \Mapping
    0.06
     मल
    0.06
    pak
    0.06
    amoto
    0.06
    \.
    0.06
    à¸Ľà¸£
    0.06
     çģ
    0.06
    ERVED
    0.06
     prest
    0.06
    Activations Density 0.004%

    No Known Activations