© 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. 9-LLAMASCOPE-RES-131K
    11. 96433
    Prev
    Next
    INDEX
    Explanations

    positive descriptors related to beauty and quality

    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
     divers
    -0.06
     supers
    -0.05
    Sink
    -0.05
     mist
    -0.05
    erno
    -0.05
    spi
    -0.05
    reso
    -0.05
    sing
    -0.05
     fors
    -0.05
    iras
    -0.05
    POSITIVE LOGITS
    unds
    0.07
    oslav
    0.07
    iko
    0.07
    ĨĴ
    0.06
    etti
    0.06
    -looking
    0.06
     Sheridan
    0.06
    olit
    0.06
    agle
    0.06
    .executeQuery
    0.06
    Activations Density 0.033%

    No Known Activations