© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 42797
    Prev
    Next
    INDEX
    Explanations

    terms indicating ongoing or increasing situations

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     altogether
    -0.07
    .Åŀ
    -0.06
    _hdl
    -0.06
    ">//
    -0.06
    ucken
    -0.06
    is
    -0.06
     bye
    -0.06
     Bye
    -0.06
    .VisualBasic
    -0.06
     Pill
    -0.06
    POSITIVE LOGITS
    greens
    0.10
    ÙĪÛĮÙĩ
    0.08
    -present
    0.08
    igator
    0.08
    мовÑĸÑĢ
    0.08
    green
    0.07
    LAST
    0.07
     greater
    0.07
    MORE
    0.07
    igh
    0.07
    Activations Density 0.005%

    No Known Activations