© 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. 117107
    Prev
    Next
    INDEX
    Explanations

    various units of time and age expressions

    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
    нав
    -0.06
     mil
    -0.06
     Joi
    -0.06
     nav
    -0.06
     Wig
    -0.06
    opus
    -0.06
    леÑĤ
    -0.05
    iš
    -0.05
    /power
    -0.05
    ffe
    -0.05
    POSITIVE LOGITS
    amp
    0.10
    nbsp
    0.09
    abus
    0.08
    raquo
    0.08
    ï¸ı
    0.08
    ÌĨ
    0.07
    ventus
    0.07
    ãģ¤ãģ®
    0.07
    oro
    0.07
    -REAL
    0.07
    Activations Density 0.097%

    No Known Activations