© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 125979
    Prev
    Next
    INDEX
    Explanations

    references to the term "laurel" and its variations, indicating honor or recognition

    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
    builder
    -0.07
    getAs
    -0.07
    osta
    -0.06
    mah
    -0.06
    pherd
    -0.06
    elsen
    -0.06
    uos
    -0.06
     foreground
    -0.06
    lights
    -0.06
    .multipart
    -0.06
    POSITIVE LOGITS
    erdale
    0.07
     Deg
    0.07
    abyrinth
    0.07
    esome
    0.06
     Vec
    0.06
    anne
    0.06
    ice
    0.06
     Lumpur
    0.06
    erence
    0.06
    zos
    0.06
    Activations Density 0.011%

    No Known Activations