© 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. 76600
    Prev
    Next
    INDEX
    Explanations

    references to the need for additional information or options

    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
    iec
    -0.08
    DMI
    -0.08
    defgroup
    -0.07
    resh
    -0.07
    anka
    -0.07
    ãģıãģł
    -0.07
    isko
    -0.07
    práv
    -0.07
    _msgs
    -0.07
    ĺIJ
    -0.07
    POSITIVE LOGITS
     or
    0.07
     space
    0.07
     detail
    0.07
     information
    0.07
     resources
    0.06
    duto
    0.06
     credits
    0.06
     persu
    0.06
     details
    0.06
     Mil
    0.06
    Activations Density 0.011%

    No Known Activations