© 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. 85080
    Prev
    Next
    INDEX
    Explanations

    references to legal or medical regulations and their implications

    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
    lify
    -0.07
    èŃľ
    -0.07
    urgy
    -0.07
    omez
    -0.07
    onica
    -0.06
    رÙĪÙħ
    -0.06
    vail
    -0.06
    èªĮ
    -0.06
    onds
    -0.06
    onomy
    -0.06
    POSITIVE LOGITS
    atu
    0.08
    ÑĨеп
    0.06
     Lump
    0.06
    hap
    0.06
    GenericType
    0.06
    unk
    0.06
    ith
    0.06
     tw
    0.06
     muse
    0.06
    por
    0.06
    Activations Density 0.018%

    No Known Activations