© 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. 39259
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to assumptions and conditions

    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
     helicopt
    -0.07
    ãĥ©ãĥ³ãĤ¹
    -0.07
     åŁ
    -0.07
     tread
    -0.07
    ptune
    -0.07
    .scalablytyped
    -0.06
    åĿĬ
    -0.06
    @Id
    -0.06
    _lcd
    -0.06
    incinn
    -0.06
    POSITIVE LOGITS
    .DataVisualization
    0.07
    ediator
    0.06
    olib
    0.06
    .lon
    0.06
    arend
    0.06
     installation
    0.06
     Bubble
    0.06
    uyết
    0.06
    erchant
    0.06
    onn
    0.06
    Activations Density 0.000%

    No Known Activations