© 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. 107586
    Prev
    Next
    INDEX
    Explanations

    references to structural integrity and potential hazards related to buildings or constructions

    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
    #
    -0.10
    بÙĪاسطة
    -0.07
     wreckage
    -0.07
    ืà¸Ń
    -0.07
    foil
    -0.07
     tez
    -0.07
     elektronik
    -0.07
    eldo
    -0.07
    iets
    -0.07
    OptionsResolver
    -0.07
    POSITIVE LOGITS
     structural
    0.11
     structure
    0.09
     struct
    0.09
     stability
    0.09
     building
    0.09
     Structural
    0.08
    structural
    0.08
     foundation
    0.08
     unstable
    0.08
    Struct
    0.08
    Activations Density 0.009%

    No Known Activations