© 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. 104945
    Prev
    Next
    INDEX
    Explanations

    information related to digital content uploads and dates

    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
    ival
    -0.07
    cke
    -0.06
    etro
    -0.06
    Ë
    -0.06
    SENT
    -0.06
     rival
    -0.05
    alist
    -0.05
     Chun
    -0.05
    ister
    -0.05
    ince
    -0.05
    POSITIVE LOGITS
    bette
    0.09
    gratis
    0.07
    .ud
    0.07
    Vtbl
    0.06
    оÑĹ
    0.06
    ëľ
    0.06
    ToProps
    0.06
    dera
    0.06
    bucks
    0.06
     Mills
    0.06
    Activations Density 0.001%

    No Known Activations