© 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. 40907
    Prev
    Next
    INDEX
    Explanations

    phrases indicating future actions or events

    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
    sein
    -0.07
    ä¼ģ
    -0.07
    ulse
    -0.07
    uir
    -0.07
    StateChanged
    -0.07
    irs
    -0.06
    atie
    -0.06
    \CMS
    -0.06
     incid
    -0.06
    خت
    -0.06
    POSITIVE LOGITS
    enerima
    0.07
    NullException
    0.06
    inker
    0.06
    zer
    0.06
    retorno
    0.06
    agos
    0.06
    Soon
    0.06
     soon
    0.06
    Defaults
    0.06
    omor
    0.06
    Activations Density 0.012%

    No Known Activations