© 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. 88667
    Prev
    Next
    INDEX
    Explanations

    phrases expressing positive qualities or experiences

    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
     Shed
    -0.07
    oku
    -0.07
    ÑĨÑĥ
    -0.07
    ayment
    -0.06
    ÑģÑĤÑĢи
    -0.06
    ãģ¾ãģ¾
    -0.06
    Æ¡n
    -0.06
     ones
    -0.06
    olle
    -0.06
     Mog
    -0.06
    POSITIVE LOGITS
    contrast
    0.07
     contrast
    0.07
     finely
    0.07
    اÙħÙĬ
    0.07
    iks
    0.06
    acket
    0.06
     lovely
    0.06
     deal
    0.06
    @ResponseBody
    0.06
    Eigen
    0.06
    Activations Density 0.005%

    No Known Activations