© 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. 28073
    Prev
    Next
    INDEX
    Explanations

    references to age or age-related descriptors

    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
     lifelong
    -0.07
     late
    -0.07
    ượt
    -0.06
     frü
    -0.06
    Typed
    -0.06
    eo
    -0.06
     early
    -0.06
     Lifetime
    -0.06
    Markup
    -0.06
     Late
    -0.05
    POSITIVE LOGITS
    -fashioned
    0.13
    ablish
    0.10
    /new
    0.10
    -old
    0.09
    Ŀ
    0.09
     fashioned
    0.08
    /original
    0.08
    é¾Ħ
    0.08
    ÅĻich
    0.08
     ÙħÛĮÙĦادÛĮ
    0.07
    Activations Density 0.021%

    No Known Activations