© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 103233
    Prev
    Next
    INDEX
    Explanations

    HTML attributes and class definitions in code snippets

    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
    ropoda
    -0.07
     vej
    -0.07
    ovich
    -0.07
    raya
    -0.07
    enchmark
    -0.06
    ién
    -0.06
    lom
    -0.06
    ihn
    -0.06
    lied
    -0.06
    elsen
    -0.06
    POSITIVE LOGITS
    clearfix
    0.07
    setItem
    0.06
     decltype
    0.06
     Mis
    0.06
     Scho
    0.06
     uchar
    0.06
    stitutions
    0.06
    implify
    0.06
    æĭ©
    0.06
    gy
    0.06
    Activations Density 0.017%

    No Known Activations