© 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. 94660
    Prev
    Next
    INDEX
    Explanations

    nuances of romantic relationships and wedding events

    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
    èĪĮ
    -0.07
    sted
    -0.07
    оÑģÑĤ
    -0.07
    osti
    -0.06
    ADF
    -0.06
    NewLabel
    -0.06
    ê°¤
    -0.06
    eroon
    -0.06
    wg
    -0.06
    erton
    -0.06
    POSITIVE LOGITS
    fr
    0.06
     fr
    0.06
    gent
    0.06
     gentleman
    0.06
     gent
    0.06
     Yüz
    0.06
    _OID
    0.06
    fol
    0.06
    anch
    0.06
    лаÑĢа
    0.06
    Activations Density 0.032%

    No Known Activations