© 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. 372
    Prev
    Next
    INDEX
    Explanations

    references to herbal extracts and their health benefits

    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
    ous
    -0.06
    ories
    -0.06
    optera
    -0.06
     tm
    -0.06
     necessarily
    -0.06
    AMPL
    -0.06
    organic
    -0.06
     res
    -0.06
    622
    -0.06
    419
    -0.05
    POSITIVE LOGITS
    ấu
    0.08
    adar
    0.08
    idth
    0.07
    ấp
    0.07
    Ưá»
    0.07
    _GRANTED
    0.07
    ạc
    0.07
    adero
    0.07
    ãĤĥ
    0.07
    ằng
    0.07
    Activations Density 0.010%

    No Known Activations