© 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. 77275
    Prev
    Next
    INDEX
    Explanations

    references to educational performance metrics

    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
    á»ģ
    -0.07
    าà¸Ķ
    -0.06
    UNIX
    -0.06
    ož
    -0.06
     Sabha
    -0.06
     UNU
    -0.06
    _NEED
    -0.06
     Dancing
    -0.06
    hoe
    -0.06
    CTX
    -0.06
    POSITIVE LOGITS
     test
    0.09
     measuring
    0.08
    test
    0.07
    ertest
    0.07
     testing
    0.07
     tests
    0.07
    zeug
    0.07
     Test
    0.06
    strand
    0.06
    AdapterManager
    0.06
    Activations Density 0.005%

    No Known Activations