© 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. 128179
    Prev
    Next
    INDEX
    Explanations

    phrases indicating upcoming events or trends

    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
    ÑĮ
    -0.08
    лин
    -0.07
     Dro
    -0.06
    igner
    -0.06
    Ñħ
    -0.06
    ÑĤÑĮ
    -0.06
    im
    -0.06
     ÙĨÙĪÙģ
    -0.06
    imet
    -0.06
     Hod
    -0.05
    POSITIVE LOGITS
    /down
    0.14
    ILON
    0.08
    PCS
    0.07
    -down
    0.07
     ante
    0.07
    ToDate
    0.07
    urum
    0.07
    indre
    0.07
    osu
    0.07
    enie
    0.07
    Activations Density 0.028%

    No Known Activations