© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 75553
    Prev
    Next
    INDEX
    Explanations

    terms related to the rental and manufacturing history of objects, particularly transportation and materials

    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
     opak
    -0.09
    phas
    -0.08
     cigaret
    -0.07
    andez
    -0.07
    culo
    -0.06
    ãĥ¼ãĥij
    -0.06
     currently
    -0.06
     Redistributions
    -0.06
     cripp
    -0.06
    idl
    -0.06
    POSITIVE LOGITS
     soon
    0.08
     later
    0.07
    Soon
    0.07
    soon
    0.07
     STILL
    0.07
     finally
    0.07
     still
    0.07
     Soon
    0.07
     improved
    0.07
     improvements
    0.07
    Activations Density 0.006%

    No Known Activations