© 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. 126579
    Prev
    Next
    INDEX
    Explanations

    expressions of positive sentiment towards various subjects

    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
    اÙĦا
    -0.07
    requete
    -0.07
    an
    -0.07
    ught
    -0.06
    ippi
    -0.06
    çľ¾
    -0.06
    lette
    -0.06
    éģ¸æīĭ
    -0.06
    cplusplus
    -0.06
     Jude
    -0.06
    POSITIVE LOGITS
     how
    0.09
    окÑĢем
    0.07
     cómo
    0.07
    iets
    0.07
    .toolbox
    0.07
    ipel
    0.07
    enheim
    0.07
    pollo
    0.06
    nees
    0.06
    720
    0.06
    Activations Density 0.013%

    No Known Activations