© 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. 69672
    Prev
    Next
    INDEX
    Explanations

    numerical and metadata elements associated with images and URLs

    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
    ccoli
    -0.06
    quate
    -0.06
    314
    -0.06
     predis
    -0.06
    335
    -0.06
    utz
    -0.05
     tw
    -0.05
    rech
    -0.05
    sville
    -0.05
     esc
    -0.05
    POSITIVE LOGITS
     Morm
    0.08
    .scalablytyped
    0.07
    Converted
    0.07
    лини
    0.07
    #ad
    0.07
    Æ¡
    0.07
     ÐĴики
    0.07
    SPATH
    0.07
    converted
    0.07
    _conversion
    0.07
    Activations Density 0.014%

    No Known Activations