© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 27543
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ntag
    -0.07
     å¾ĴæŃ©
    -0.07
    outputs
    -0.07
    cher
    -0.06
    plevel
    -0.06
    APT
    -0.06
    nf
    -0.06
    qli
    -0.06
    hesion
    -0.06
    ongoose
    -0.06
    POSITIVE LOGITS
    lor
    0.06
    /stdc
    0.06
     Fairfield
    0.06
     locally
    0.06
    &a
    0.06
    اÙĪÛĮ
    0.06
     åº
    0.06
    andom
    0.06
    st
    0.06
     proudly
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.