© 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. 9-LLAMASCOPE-RES-131K
    11. 94856
    Prev
    Next
    INDEX
    Explanations

    references to romantic relationships and love letters

    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
    overe
    -0.07
    wig
    -0.06
    inde
    -0.06
    ewitness
    -0.06
     Signature
    -0.06
    azing
    -0.06
    wart
    -0.06
    /cgi
    -0.06
    ãģķãģĽ
    -0.06
    res
    -0.06
    POSITIVE LOGITS
     Yön
    0.08
    âu
    0.07
    omik
    0.06
    IOD
    0.06
    olean
    0.06
    리카
    0.06
    ampler
    0.06
    .shared
    0.06
    Ĭ
    0.06
    .isDefined
    0.06
    Activations Density 0.060%

    No Known Activations