© 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. 15468
    Prev
    Next
    INDEX
    Explanations

    expressions related to personal aspirations and the passage of time

    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
    åī²
    -0.07
     boÄŁ
    -0.07
    ÑĩаÑģÑĤ
    -0.07
    SIDE
    -0.07
    orama
    -0.07
    peria
    -0.07
    δÏĮ
    -0.07
    éĥİ
    -0.06
    ома
    -0.06
    á»ĵ
    -0.06
    POSITIVE LOGITS
     death
    0.10
     retirement
    0.10
     die
    0.09
     retire
    0.09
     Death
    0.08
     died
    0.08
     dying
    0.08
     pension
    0.08
     age
    0.07
     terminal
    0.07
    Activations Density 0.024%

    No Known Activations