© 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. 87460
    Prev
    Next
    INDEX
    Explanations

    expressions indicating insight into various experiences and perspectives

    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
    dea
    -0.09
    ushman
    -0.07
    -Sah
    -0.07
    watch
    -0.07
    ÑĢок
    -0.07
    jeme
    -0.07
    dech
    -0.07
    ellan
    -0.07
    (æ°´
    -0.07
     Verfüg
    -0.07
    POSITIVE LOGITS
     how
    0.10
     behind
    0.09
     why
    0.08
     worlds
    0.08
     lives
    0.08
     recess
    0.07
     life
    0.07
     world
    0.07
    how
    0.07
     process
    0.07
    Activations Density 0.021%

    No Known Activations