© 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. 16479
    Prev
    Next
    INDEX
    Explanations

    themes related to stability and changes over time in life

    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
    rk
    -0.07
    £i
    -0.06
    rych
    -0.06
    emoth
    -0.06
    rup
    -0.06
    ument
    -0.06
     nullptr
    -0.06
    ounded
    -0.06
    allon
    -0.06
    igate
    -0.05
    POSITIVE LOGITS
     core
    0.10
     unchanged
    0.09
     constant
    0.09
    core
    0.09
    _core
    0.09
     ثابت
    0.09
    -core
    0.09
    (always
    0.09
     steady
    0.08
     constants
    0.08
    Activations Density 0.016%

    No Known Activations