© 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. 15-LLAMASCOPE-RES-131K
    11. 86519
    Prev
    Next
    INDEX
    Explanations

    elements related to social dynamics and class struggles

    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
    kus
    -0.07
     Venue
    -0.06
    /cms
    -0.06
     ÑĥÑģ
    -0.05
    iveau
    -0.05
     effective
    -0.05
    èĪĮ
    -0.05
    �t
    -0.05
     venue
    -0.05
    onomous
    -0.05
    POSITIVE LOGITS
     fucked
    0.07
    encil
    0.07
    âĻ¡
    0.07
    319
    0.07
    unset
    0.06
    apol
    0.06
    .lazy
    0.06
     neoliberal
    0.06
    late
    0.06
    sealed
    0.06
    Activations Density 0.002%

    No Known Activations