© 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. 106488
    Prev
    Next
    INDEX
    Explanations

    expressions of anticipation or eagerness

    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
    och
    -0.07
    alk
    -0.07
    als
    -0.06
    .datab
    -0.06
     Matters
    -0.06
    ologne
    -0.06
    han
    -0.06
     matters
    -0.06
    ott
    -0.06
    enger
    -0.05
    POSITIVE LOGITS
    illac
    0.09
     hearing
    0.09
     nieu
    0.07
     updates
    0.07
    (Op
    0.07
    killer
    0.07
     seeing
    0.07
    hear
    0.07
    eldon
    0.07
    .await
    0.07
    Activations Density 0.014%

    No Known Activations