© 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. 107700
    Prev
    Next
    INDEX
    Explanations

    references to individuals in supportive or subordinate government roles

    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
    pell
    -0.08
    roje
    -0.07
    etik
    -0.07
    æł·çļĦ
    -0.07
    BuilderInterface
    -0.07
    suite
    -0.07
    ÙĪÙĬس
    -0.07
    mel
    -0.07
    mi
    -0.07
    ucs
    -0.07
    POSITIVE LOGITS
     mayor
    0.07
    ities
    0.06
    bh
    0.06
    ศาสà¸ķร
    0.06
    vrier
    0.06
    lift
    0.06
    cription
    0.06
    ure
    0.06
    aux
    0.06
    agon
    0.06
    Activations Density 0.003%

    No Known Activations