© 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. 80300
    Prev
    Next
    INDEX
    Explanations

    references to romantic relationships and dating

    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
    osu
    -0.07
    hek
    -0.07
    Ãło
    -0.06
    owers
    -0.06
     Reform
    -0.06
    åİĭ
    -0.06
    endoza
    -0.06
     kür
    -0.06
    byt
    -0.06
    sembly
    -0.06
    POSITIVE LOGITS
    robat
    0.07
     Hay
    0.06
    usat
    0.06
    694
    0.06
    ilig
    0.06
    CanBe
    0.06
    654
    0.06
     Walton
    0.06
     Cannot
    0.06
    ìĿĮ
    0.06
    Activations Density 0.012%

    No Known Activations