© 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. 15-LLAMASCOPE-RES-131K
    11. 87448
    Prev
    Next
    INDEX
    Explanations

    elements related to publishing and printing information

    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
    ucci
    -0.07
     Magazine
    -0.07
     Alternate
    -0.07
     magazines
    -0.06
     magazine
    -0.06
    agnar
    -0.06
    empo
    -0.06
    sci
    -0.06
    ukes
    -0.06
    pite
    -0.06
    POSITIVE LOGITS
     Hüs
    0.07
    DownList
    0.07
    DITION
    0.06
    ç²¾
    0.06
    íĿ
    0.06
    psilon
    0.06
     prostitut
    0.06
    å¯Ŀ
    0.06
    اط
    0.06
    æ´
    0.06
    Activations Density 0.002%

    No Known Activations