© 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. 15416
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating actions or states of being

    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
    inion
    -0.06
    ãĥĭãĥ¼
    -0.06
    thus
    -0.06
    æĿ¡
    -0.06
    .micro
    -0.06
    ابت
    -0.06
     Jeh
    -0.06
    obe
    -0.06
    ssue
    -0.06
     Bust
    -0.06
    POSITIVE LOGITS
    isol
    0.07
    agas
    0.07
    ahoma
    0.07
    amp
    0.06
    illa
    0.06
    Navigator
    0.06
    RITE
    0.06
    iddi
    0.06
    ZY
    0.06
    ³
    0.06
    Activations Density 0.005%

    No Known Activations