© 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. 60450
    Prev
    Next
    INDEX
    Explanations

    references to future events or concepts

    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
    chter
    -0.08
    shire
    -0.07
    pany
    -0.07
    kontakte
    -0.07
    ãĥªãĥ¼ãĤº
    -0.07
    249
    -0.07
    égor
    -0.07
    üçük
    -0.06
    furt
    -0.06
    ignon
    -0.06
    POSITIVE LOGITS
    -proof
    0.07
     Future
    0.07
    ane
    0.07
     future
    0.07
    .Future
    0.06
     tense
    0.06
     Syn
    0.06
     Fore
    0.06
    Splash
    0.06
    istically
    0.06
    Activations Density 0.008%

    No Known Activations