© 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. 125151
    Prev
    Next
    INDEX
    Explanations

    terms related to the state of being or existence

    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
     inn
    -0.06
    igan
    -0.06
     e
    -0.06
     exists
    -0.06
    -0.06
     ok
    -0.06
     start
    -0.06
     existed
    -0.06
    inn
    -0.06
     subsequent
    -0.06
    POSITIVE LOGITS
     accordingly
    0.08
     PartialView
    0.08
    ÑģÑĤиÑĤ
    0.07
    áky
    0.07
    clave
    0.07
    گاب
    0.07
    коÑĤ
    0.07
    ække
    0.07
    isyon
    0.07
     ciz
    0.07
    Activations Density 0.124%

    No Known Activations