© 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. 41950
    Prev
    Next
    INDEX
    Explanations

    instances of the word "just" and its surrounding context, indicating a focus on casual or informal discourse

    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
    utch
    -0.07
     although
    -0.07
    achuset
    -0.06
     BUT
    -0.06
    inee
    -0.06
     but
    -0.06
    ayne
    -0.06
    AFX
    -0.06
    .mit
    -0.06
    Ấ
    -0.06
    POSITIVE LOGITS
     ones
    0.07
    oven
    0.07
     اÛĮÙĨÚ©Ùĩ
    0.06
    Timing
    0.06
     INTERRU
    0.06
     Lumpur
    0.06
    oice
    0.06
    наÑĩе
    0.06
    uitka
    0.06
    SceneManager
    0.06
    Activations Density 0.019%

    No Known Activations