© 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. 73846
    Prev
    Next
    INDEX
    Explanations

    elements related to interior design and space optimization

    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
    podob
    -0.07
    assi
    -0.06
    args
    -0.06
    isko
    -0.06
     coronavirus
    -0.06
    anzeigen
    -0.06
    rej
    -0.06
    lid
    -0.06
    iag
    -0.06
    ãģĵãĤĵãģ«
    -0.06
    POSITIVE LOGITS
    elden
    0.06
    æĦı
    0.06
    ancial
    0.06
     Hack
    0.06
    isay
    0.06
    MMdd
    0.06
    Cipher
    0.06
    çŃĭ
    0.06
     xuyên
    0.06
    ocha
    0.06
    Activations Density 0.002%

    No Known Activations