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

    Neuronpedia

    Jacobian LensNEW
    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. 88780
    Prev
    Next
    INDEX
    Explanations

    phrases indicating possession or having certain attributes

    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
    .mousePosition
    -0.07
    ONA
    -0.07
    osti
    -0.07
    shan
    -0.06
    AWN
    -0.06
    βι
    -0.06
    illon
    -0.06
    anko
    -0.06
    ypsum
    -0.06
     گرد
    -0.06
    POSITIVE LOGITS
    pta
    0.07
     understanding
    0.07
    a
    0.06
     someone
    0.06
     willing
    0.06
    ëĿ½
    0.06
    ì¶ķ
    0.06
     adequate
    0.06
    CAF
    0.06
    ëĭ¨
    0.06
    Activations Density 0.019%

    No Known Activations