© 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. 14931
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to lifespan and durability of objects

    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
    ihn
    -0.07
     tolerated
    -0.06
    -level
    -0.06
     ÑĥÑĢовнÑı
    -0.06
    .Safe
    -0.06
    urrent
    -0.06
    Ñĩин
    -0.06
    angel
    -0.06
     bure
    -0.06
    onec
    -0.06
    POSITIVE LOGITS
    RelativeTo
    0.07
    VERTISE
    0.07
    -long
    0.07
    ytut
    0.07
    ueur
    0.07
     extension
    0.07
    evity
    0.07
    issement
    0.07
     expectancy
    0.07
     span
    0.07
    Activations Density 0.015%

    No Known Activations