© 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. 16555
    Prev
    Next
    INDEX
    Explanations

    HTML attributes and elements related to user input forms

    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
    ktop
    -0.08
    VOKE
    -0.07
    avis
    -0.07
    اÙģت
    -0.07
    arget
    -0.07
    isFunction
    -0.07
    uze
    -0.07
    gebn
    -0.07
    .sep
    -0.07
     оÑĢганиза
    -0.07
    POSITIVE LOGITS
    ¼åIJĪ
    0.06
     winds
    0.06
     tel
    0.05
     nowhere
    0.05
    otu
    0.05
    kin
    0.05
    reet
    0.05
     noqa
    0.05
    962
    0.05
    arius
    0.05
    Activations Density 0.002%

    No Known Activations