© 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. 93018
    Prev
    Next
    INDEX
    Explanations

    references to quantities and proportions in various contexts

    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
    bury
    -0.07
    ries
    -0.06
     among
    -0.06
    uru
    -0.06
    enu
    -0.06
    خة
    -0.06
    ess
    -0.06
     burial
    -0.06
     -
    -0.05
     one
    -0.05
    POSITIVE LOGITS
     ëĮĢë¶Ģë¶Ħ
    0.08
    undy
    0.08
     focus
    0.08
    SharedPointer
    0.07
    focus
    0.07
    @n
    0.07
    ÙĬÙĦÙĬ
    0.07
    -focus
    0.07
    currentColor
    0.07
    Å¡ek
    0.07
    Activations Density 0.025%

    No Known Activations