© 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. 89460
    Prev
    Next
    INDEX
    Explanations

    the word "some" in various contexts, indicating an interest in quantity or assortment

    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
    ritch
    -0.07
    orig
    -0.06
    ritz
    -0.06
    ,LOCATION
    -0.06
    osemite
    -0.06
    ADA
    -0.06
     perse
    -0.06
    395
    -0.06
    ont
    -0.06
     cliente
    -0.06
    POSITIVE LOGITS
    /all
    0.10
    place
    0.07
    ones
    0.07
    pon
    0.07
    ht
    0.07
    assen
    0.07
     proper
    0.07
     real
    0.07
     sort
    0.07
     serious
    0.06
    Activations Density 0.041%

    No Known Activations