© 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. 29236
    Prev
    Next
    INDEX
    Explanations

    numerical values representing anniversaries or significant milestones

    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
     Horton
    -0.07
    ogne
    -0.06
    à¤ľà¤¨
    -0.06
    gid
    -0.05
    ton
    -0.05
     Buch
    -0.05
     stuff
    -0.05
     lay
    -0.05
    _ONCE
    -0.05
    als
    -0.05
    POSITIVE LOGITS
     anniversary
    0.08
    zek
    0.07
    storybook
    0.07
    jit
    0.07
    th
    0.07
     anale
    0.07
     consect
    0.07
    abela
    0.07
    FTWARE
    0.07
    -ce
    0.07
    Activations Density 0.008%

    No Known Activations