© 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. 9-LLAMASCOPE-RES-131K
    11. 97720
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to chemical and biological measurement methods

    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
    /us
    -0.07
    achi
    -0.06
    ore
    -0.06
    /animations
    -0.05
    eselect
    -0.05
    errals
    -0.05
    hare
    -0.05
    strup
    -0.05
    wen
    -0.05
     deb
    -0.05
    POSITIVE LOGITS
    quo
    0.07
    lla
    0.07
    ekim
    0.07
    quia
    0.07
    yk
    0.07
    524
    0.07
    _contrib
    0.07
    odont
    0.07
     jos
    0.07
    ioc
    0.07
    Activations Density 0.009%

    No Known Activations