© 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. 15-LLAMASCOPE-RES-131K
    11. 88986
    Prev
    Next
    INDEX
    Explanations

    gerunds and present participles, particularly related to actions or processes

    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
    दम
    -0.07
    ãĥ¼ãĤº
    -0.07
    yo
    -0.07
    edImage
    -0.07
    ingen
    -0.07
     perse
    -0.07
    ibo
    -0.07
    ogue
    -0.07
    .sky
    -0.07
     Apprentice
    -0.06
    POSITIVE LOGITS
     oneself
    0.08
    semble
    0.07
    theValue
    0.07
    isia
    0.07
    -the
    0.06
    ly
    0.06
    oling
    0.06
    Ùİا
    0.06
    /build
    0.06
    /up
    0.06
    Activations Density 0.032%

    No Known Activations