© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 71768
    Prev
    Next
    INDEX
    Explanations

    numerical or performance-related data in a structured format

    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
    uren
    -0.08
    uther
    -0.07
    hiro
    -0.06
    reste
    -0.06
    à¸Ķà¸Ļ
    -0.06
    ington
    -0.06
    wich
    -0.06
    mour
    -0.06
    ковоÑĹ
    -0.06
     Rare
    -0.06
    POSITIVE LOGITS
    defgroup
    0.07
    uai
    0.07
    _DIGEST
    0.07
     ...,
    0.07
    ovna
    0.06
    (ur
    0.06
    ground
    0.06
    indi
    0.06
     Kirk
    0.06
    éłĺ
    0.06
    Activations Density 0.000%

    No Known Activations