© 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 EvalsExportsAPI 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. 78522
    Prev
    Next
    INDEX
    Explanations

    concepts related to significant life changes and challenges

    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
    075
    -0.07
    AZE
    -0.07
    ãĥ³ãĥij
    -0.07
    _CI
    -0.07
    (Display
    -0.07
     incid
    -0.07
    \OptionsResolver
    -0.07
    ãĥ¼ãĥª
    -0.07
    eri
    -0.07
    insi
    -0.07
    POSITIVE LOGITS
     opportunity
    0.07
     opportunities
    0.07
     a
    0.07
     lifetime
    0.07
     potentially
    0.07
     chance
    0.07
     possibility
    0.06
     eventual
    0.06
    ritt
    0.06
     lots
    0.06
    Activations Density 0.082%

    No Known Activations