© 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. 78531
    Prev
    Next
    INDEX
    Explanations

    references to companies and engineering-related terms

    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
    arent
    -0.06
     ä½IJ
    -0.06
     meme
    -0.06
     pdf
    -0.06
    eph
    -0.06
    RIPT
    -0.06
    _stderr
    -0.06
    thane
    -0.05
    appa
    -0.05
    odic
    -0.05
    POSITIVE LOGITS
    вÑģÑı
    0.08
    âĹİ
    0.07
    ãĥ¼ãĥį
    0.07
    RootElement
    0.07
    æĨ
    0.07
    <decimal
    0.06
    âĨĴâĨĴ
    0.06
    ucz
    0.06
    çĸĨ
    0.06
    avery
    0.06
    Activations Density 0.003%

    No Known Activations