© 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. 105099
    Prev
    Next
    INDEX
    Explanations

    references to the term "old" in various contexts, often to describe outdated ideas, systems, or demographics

    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
    γκ
    -0.08
    alo
    -0.07
    hots
    -0.06
    lah
    -0.06
    .ss
    -0.06
    dete
    -0.06
    lez
    -0.06
    तर
    -0.06
    bih
    -0.06
    женÑĮ
    -0.06
    POSITIVE LOGITS
     old
    0.11
    -old
    0.10
    old
    0.10
     traditional
    0.09
    (old
    0.09
    traditional
    0.09
    -established
    0.08
    trad
    0.08
     tradition
    0.08
    Trad
    0.08
    Activations Density 0.024%

    No Known Activations