© 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. 90633
    Prev
    Next
    INDEX
    Explanations

    academic degrees and qualifications

    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
    /XML
    -0.06
    ä¹Ļ
    -0.06
    SSERT
    -0.06
     Tops
    -0.06
    794
    -0.06
    ãĤ¢ãĥ³
    -0.05
    adesh
    -0.05
    ming
    -0.05
    isches
    -0.05
    ischen
    -0.05
    POSITIVE LOGITS
    iterr
    0.07
    apon
    0.07
    argout
    0.06
    ease
    0.06
    eger
    0.06
    ScrollBar
    0.06
    isser
    0.06
    _goals
    0.06
    argo
    0.06
    TYPO
    0.06
    Activations Density 0.045%

    No Known Activations