© 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 EvalsExportsinterp-engineNEWAPI 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. 30398
    Prev
    Next
    INDEX
    Explanations

    references to the word "Boulevard."

    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
    birth
    -0.07
    unate
    -0.07
    orz
    -0.07
    ãĥ³ãĤ¯
    -0.07
    unic
    -0.07
    .sax
    -0.07
    __/
    -0.07
    ConfigurationException
    -0.07
    alach
    -0.07
    PACK
    -0.07
    POSITIVE LOGITS
    erville
    0.06
    ville
    0.06
    illon
    0.06
    y
    0.06
    wor
    0.06
    kova
    0.05
     Claude
    0.05
    æĴ°
    0.05
    mars
    0.05
     Wolver
    0.05
    Activations Density 0.011%

    No Known Activations