© 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. 15-LLAMASCOPE-RES-131K
    11. 164
    Prev
    Next
    INDEX
    Explanations

    descriptors related to clarity and simplicity

    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
    ÑĢаÑħов
    -0.07
    æĥ
    -0.07
    ynos
    -0.06
    -Sah
    -0.06
    ington
    -0.06
    quist
    -0.06
    ((__
    -0.06
    .DefaultCellStyle
    -0.06
    impan
    -0.06
    ensitivity
    -0.06
    POSITIVE LOGITS
     straightforward
    0.12
     simplicity
    0.12
     easy
    0.10
     simple
    0.10
     simpler
    0.10
    simple
    0.10
     fácil
    0.09
    /simple
    0.09
    easy
    0.09
     easier
    0.09
    Activations Density 0.057%

    No Known Activations