© 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. 273
    Prev
    Next
    INDEX
    Explanations

    references to gifting or creating items for others

    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
    edik
    -0.08
     Streets
    -0.07
    ĨĴ
    -0.07
    ges
    -0.07
    Ìģ
    -0.06
    ierge
    -0.06
    ä¸Ī夫
    -0.06
    åĿĬ
    -0.06
     helicopt
    -0.06
    orer
    -0.06
    POSITIVE LOGITS
     myself
    0.08
     upcoming
    0.07
    ipse
    0.07
    angstrom
    0.06
     Document
    0.06
    _signature
    0.06
    rak
    0.06
     propName
    0.06
    lund
    0.06
    nst
    0.06
    Activations Density 0.014%

    No Known Activations