© 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 EvalsExportsAPI 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. 59252
    Prev
    Next
    INDEX
    Explanations

    references to mechanical operations and control systems in machinery

    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
    andest
    -0.07
    elman
    -0.07
    alat
    -0.06
    íij¸
    -0.06
    reach
    -0.06
    ccione
    -0.06
    tach
    -0.06
    allen
    -0.06
     kar
    -0.06
    erca
    -0.06
    POSITIVE LOGITS
    ÙĪÙĨÛĮ
    0.07
    nings
    0.06
     rejo
    0.06
     Sands
    0.06
    ños
    0.06
    uite
    0.06
    anteed
    0.06
    lep
    0.06
    æĺŃ
    0.06
     Pope
    0.06
    Activations Density 0.028%

    No Known Activations