© 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. 2190
    Prev
    Next
    INDEX
    Explanations

    terms related to construction and material efficiency

    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
    //{{
    -0.07
    acho
    -0.07
    gard
    -0.07
    .crm
    -0.07
    linkplain
    -0.06
    ofilm
    -0.06
     giÃłu
    -0.06
    kili
    -0.06
     صاد
    -0.06
    çĴ
    -0.06
    POSITIVE LOGITS
     structure
    0.15
     structural
    0.12
     Structure
    0.12
     structures
    0.12
    structure
    0.11
    Structure
    0.11
    _structure
    0.11
     steel
    0.10
     Structures
    0.10
     STRUCT
    0.10
    Activations Density 0.135%

    No Known Activations