© 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. 40781
    Prev
    Next
    INDEX
    Explanations

    expressions related to illumination or showcasing excellence

    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
    tings
    -0.07
    cheng
    -0.07
    uali
    -0.07
    sson
    -0.07
    leans
    -0.07
    isy
    -0.07
    atee
    -0.07
    artment
    -0.07
    slash
    -0.07
    ussian
    -0.07
    POSITIVE LOGITS
    ingly
    0.08
    ERGY
    0.07
     brightest
    0.07
     bright
    0.07
    оÑĩ
    0.07
     Belt
    0.06
    pear
    0.06
    ITIZE
    0.06
    亮
    0.06
    quiry
    0.06
    Activations Density 0.004%

    No Known Activations