© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 127237
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Ruby."

    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
    ingo
    -0.07
    uly
    -0.07
    .scalablytyped
    -0.07
    pun
    -0.07
    ima
    -0.07
    ifter
    -0.06
    mailbox
    -0.06
    907
    -0.06
    uman
    -0.06
    otte
    -0.06
    POSITIVE LOGITS
    anni
    0.08
    fruit
    0.07
    lish
    0.07
    illez
    0.07
    vale
    0.07
    ç·Ĵ
    0.07
    arez
    0.07
    gems
    0.07
    brook
    0.07
    ocator
    0.06
    Activations Density 0.002%

    No Known Activations