© 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. 81373
    Prev
    Next
    INDEX
    Explanations

    phrases and variations related to the act of submitting forms or applications

    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
    usto
    -0.07
    uries
    -0.07
    AKE
    -0.07
     Cách
    -0.07
    ackers
    -0.07
    ạp
    -0.06
    ureka
    -0.06
    indow
    -0.06
    alm
    -0.06
    oes
    -0.06
    POSITIVE LOGITS
     proposals
    0.07
     proposal
    0.07
    ante
    0.07
     IRequest
    0.07
    412
    0.06
     Diss
    0.06
    ÏĢοÏį
    0.06
    yst
    0.06
    cher
    0.06
    -valu
    0.06
    Activations Density 0.011%

    No Known Activations