© 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. 119360
    Prev
    Next
    INDEX
    Explanations

    terms related to scrolling and animation in web development

    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
    quito
    -0.07
    NECT
    -0.07
    ngör
    -0.07
    ENSE
    -0.07
    AAF
    -0.06
    ebe
    -0.06
    elman
    -0.06
    çĶŁåij½
    -0.06
    еп
    -0.06
    branch
    -0.06
    POSITIVE LOGITS
    scrollTop
    0.10
    .scrollTop
    0.10
    .Scroll
    0.10
     scrollTop
    0.09
     scroll
    0.09
     Scroll
    0.09
    Scroll
    0.08
    -scroll
    0.08
     scrolls
    0.08
    æ»
    0.08
    Activations Density 0.046%

    No Known Activations