© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 4099
    Prev
    Next
    INDEX
    Explanations

    references to locations and places, especially in descriptive narratives

    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
    /doc
    -0.07
    алÑİ
    -0.07
     Ceiling
    -0.07
    anco
    -0.06
    anh
    -0.06
    -anchor
    -0.06
    anch
    -0.06
     kapit
    -0.06
    øre
    -0.06
    åĿĬ
    -0.06
    POSITIVE LOGITS
     places
    0.10
     place
    0.09
    ideo
    0.08
     locations
    0.08
     home
    0.07
     anywhere
    0.07
     where
    0.07
     areas
    0.07
     frequ
    0.07
     wherever
    0.07
    Activations Density 0.094%

    No Known Activations