© 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. 41579
    Prev
    Next
    INDEX
    Explanations

    topics related to societal and cultural transitions and transformations

    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
    ãĥ¼ãĥģ
    -0.07
    solete
    -0.07
    ãĥ»ãĥ»ãĥ»
    -0.07
    ä¹ħ
    -0.06
    ãĥ£
    -0.06
    isure
    -0.06
    ħn
    -0.06
    areas
    -0.06
    ainter
    -0.06
     Ø£ÙĬ
    -0.06
    POSITIVE LOGITS
     heightened
    0.07
    ilon
    0.07
     multiple
    0.06
    Va
    0.06
     increased
    0.06
     mass
    0.06
     challenge
    0.06
    wy
    0.06
     high
    0.06
     rem
    0.06
    Activations Density 0.027%

    No Known Activations