© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 87090
    Prev
    Next
    INDEX
    Explanations

    phrases that encourage immediate action or contact

    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
    athan
    -0.07
    502
    -0.06
    ug
    -0.06
     Rec
    -0.06
    rec
    -0.06
    ull
    -0.06
    757
    -0.06
    657
    -0.06
    607
    -0.06
    dit
    -0.06
    POSITIVE LOGITS
    edl
    0.08
    ipi
    0.08
    elib
    0.07
     ola
    0.07
    vip
    0.07
    Utf
    0.07
    enaire
    0.07
     tela
    0.07
    emez
    0.07
    .IContainer
    0.07
    Activations Density 0.004%

    No Known Activations