© 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. 83020
    Prev
    Next
    INDEX
    Explanations

    references to emotional states or relationships

    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
    à¸Ļà¸Ħร
    -0.08
    اتÛĮ
    -0.07
    weg
    -0.07
    ossier
    -0.07
    eton
    -0.07
    warz
    -0.07
    ÑĮ
    -0.07
    anth
    -0.06
    flt
    -0.06
    ê´Ģ
    -0.06
    POSITIVE LOGITS
    echa
    0.08
    hausen
    0.08
    naire
    0.07
    evice
    0.07
    ez
    0.07
    ing
    0.07
    naires
    0.07
    -league
    0.07
    ahn
    0.07
    eb
    0.07
    Activations Density 0.017%

    No Known Activations