© 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. 27498
    Prev
    Next
    INDEX
    Explanations

    content related to expressing love and remembrance for someone

    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
    edla
    -0.08
    寧
    -0.08
    AuthToken
    -0.07
    cona
    -0.07
     Lindsay
    -0.07
     doz
    -0.07
    eing
    -0.06
    yo
    -0.06
    alth
    -0.06
    MMC
    -0.06
    POSITIVE LOGITS
    оваÑĢ
    0.07
    _subset
    0.07
     guarante
    0.06
     Schro
    0.06
    unately
    0.06
    æ¼
    0.06
    -extension
    0.06
     popular
    0.06
    Popular
    0.06
    ansi
    0.06
    Activations Density 0.003%

    No Known Activations