© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 76014
    Prev
    Next
    INDEX
    Explanations

    words starting with "Sw" or related to the concept of swiftness

    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
    ÑĪка
    -0.08
    κÏģι
    -0.07
    amide
    -0.07
    MBProgressHUD
    -0.07
    ÑĢиз
    -0.07
    VML
    -0.07
    .scalablytyped
    -0.07
    ignum
    -0.06
    ElapsedTime
    -0.06
    oproject
    -0.06
    POSITIVE LOGITS
    stakes
    0.10
     Sw
    0.10
    /sw
    0.10
    Sw
    0.08
     sw
    0.08
    (sw
    0.07
    ollen
    0.07
    iji
    0.07
    -sw
    0.07
     SW
    0.06
    Activations Density 0.044%

    No Known Activations