© 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. 17-LLAMASCOPE-RES-131K
    11. 89034
    Prev
    Next
    INDEX
    Explanations

    numeric values associated with sentencing or legal consequences

    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
    heels
    -0.07
    ields
    -0.06
    888
    -0.06
    ones
    -0.06
    otor
    -0.06
     плен
    -0.06
    ovenant
    -0.06
    ONES
    -0.06
    jde
    -0.06
    ernes
    -0.06
    POSITIVE LOGITS
    anine
    0.08
    ppy
    0.07
    Calibri
    0.07
    лини
    0.07
    微软éĽħé»ij
    0.07
    jsonp
    0.07
    ÅĻi
    0.06
    abela
    0.06
     ArrayBuffer
    0.06
    ục
    0.06
    Activations Density 0.007%

    No Known Activations