© 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. 14899
    Prev
    Next
    INDEX
    Explanations

    specific information related to schedules and updates in various contexts

    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
     Leh
    -0.07
    beck
    -0.07
    761
    -0.06
    eyin
    -0.06
    uales
    -0.06
     Dent
    -0.06
    à¤Ĥद
    -0.06
     Fle
    -0.06
    athan
    -0.06
    ayer
    -0.06
    POSITIVE LOGITS
    ÙĪÛĮÙĩ
    0.07
    roman
    0.07
    é¦Ļ
    0.07
    iou
    0.06
    _RG
    0.06
    веÑģÑĤи
    0.06
    bare
    0.06
    /XML
    0.06
    å¬
    0.06
     coop
    0.06
    Activations Density 0.011%

    No Known Activations