© 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. 9-LLAMASCOPE-RES-131K
    11. 98741
    Prev
    Next
    INDEX
    Explanations

    terms related to legal protections and rights

    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
    anta
    -0.07
    amet
    -0.07
     onViewCreated
    -0.07
    .sponge
    -0.06
    .TestCase
    -0.06
     Rosenstein
    -0.06
    okus
    -0.06
     hÆ°á»Łng
    -0.06
    rozen
    -0.06
    lobber
    -0.06
    POSITIVE LOGITS
     against
    0.07
    .DataType
    0.07
     Commit
    0.07
    addir
    0.06
     dla
    0.06
    against
    0.06
    uzzi
    0.06
    .getProperty
    0.06
    rights
    0.06
     mer
    0.06
    Activations Density 0.012%

    No Known Activations