© 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. 17-LLAMASCOPE-RES-131K
    11. 15237
    Prev
    Next
    INDEX
    Explanations

    phrases indicating ongoing actions or situations

    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
    é¨
    -0.08
    iqueta
    -0.07
    sek
    -0.06
    indsight
    -0.06
    oca
    -0.06
    моÑĤ
    -0.06
    Ù¹
    -0.06
    zia
    -0.06
     már
    -0.06
    och
    -0.06
    POSITIVE LOGITS
    sdale
    0.07
    bilt
    0.07
    lluminate
    0.06
    acas
    0.06
     still
    0.06
    erra
    0.06
     search
    0.06
     embargo
    0.06
     pending
    0.06
     remain
    0.06
    Activations Density 0.017%

    No Known Activations