© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 70868
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to site usage and legal agreements

    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
    ARED
    -0.07
    hrad
    -0.07
     renew
    -0.07
     Renew
    -0.07
    atures
    -0.07
    รà¸ĵ
    -0.06
    oval
    -0.06
    SSI
    -0.06
    isposable
    -0.06
    isplay
    -0.06
    POSITIVE LOGITS
    eros
    0.06
    706
    0.06
    engin
    0.06
     ì¡
    0.06
    yar
    0.06
     ti
    0.06
    jax
    0.06
    icot
    0.05
    byn
    0.05
    697
    0.05
    Activations Density 0.003%

    No Known Activations