© 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. 15706
    Prev
    Next
    INDEX
    Explanations

    terms associated with placeholder text or filler content

    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
    elts
    -0.07
    regor
    -0.06
    umat
    -0.06
    _requires
    -0.06
     Ben
    -0.06
    ener
    -0.06
    ienia
    -0.06
    fan
    -0.06
     Canter
    -0.06
     presente
    -0.06
    POSITIVE LOGITS
    335
    0.07
    106
    0.06
    oks
    0.06
    (savedInstanceState
    0.06
    ãĥ«ãĥĪ
    0.06
     Weaver
    0.06
     Tas
    0.06
    elerik
    0.06
     Woody
    0.06
    ManagerInterface
    0.06
    Activations Density 0.001%

    No Known Activations