© 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. 40504
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal development and well-being

    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
    isiyle
    -0.07
    veau
    -0.07
     Civ
    -0.07
    رÛĮÙĩ
    -0.07
     bump
    -0.07
    JOR
    -0.07
    dden
    -0.06
    UILTIN
    -0.06
    quiry
    -0.06
    uer
    -0.06
    POSITIVE LOGITS
     aside
    0.11
     sail
    0.10
     apart
    0.09
     Sail
    0.08
    tle
    0.08
    tee
    0.08
     Aside
    0.08
     forth
    0.07
     abl
    0.07
    aside
    0.07
    Activations Density 0.015%

    No Known Activations