© 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. 29439
    Prev
    Next
    INDEX
    Explanations

    references to "scrap" in various contexts, indicating a focus on the theme of recycling or waste management

    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
    amics
    -0.07
    pheric
    -0.07
    estone
    -0.07
    iams
    -0.07
    ekt
    -0.06
    estar
    -0.06
    hra
    -0.06
    erate
    -0.06
    preter
    -0.06
    648
    -0.06
    POSITIVE LOGITS
    neck
    0.08
    asti
    0.07
    ede
    0.07
    stakes
    0.07
    icious
    0.07
    ski
    0.07
    booking
    0.07
    heap
    0.07
    ital
    0.07
    stin
    0.07
    Activations Density 0.005%

    No Known Activations