© 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. 3845
    Prev
    Next
    INDEX
    Explanations

    terms related to reduction or alleviation of negative impacts on health and the environment

    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
    issy
    -0.06
    /sn
    -0.06
    168
    -0.05
    ettle
    -0.05
    .xz
    -0.05
    rippling
    -0.05
     Mais
    -0.05
    cep
    -0.05
    .Framework
    -0.05
     sooner
    -0.05
    POSITIVE LOGITS
     reliance
    0.09
    /remove
    0.09
    /mit
    0.08
    idata
    0.08
    ToOne
    0.08
    ¢åįķ
    0.07
    ataka
    0.07
     dependence
    0.07
     risk
    0.07
     number
    0.07
    Activations Density 0.028%

    No Known Activations