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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 27070
    Prev
    Next
    INDEX
    Explanations

    tokens related to web tracking and parameters in URLs

    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
    hua
    -0.08
    uzzi
    -0.07
    hiba
    -0.06
    WebResponse
    -0.06
    umar
    -0.06
    um
    -0.06
    posables
    -0.06
    ides
    -0.06
    umu
    -0.06
    oney
    -0.06
    POSITIVE LOGITS
    ailer
    0.07
    dera
    0.07
    HELL
    0.07
     laut
    0.06
    .codec
    0.06
    ä¸ģ
    0.06
    inker
    0.06
    ARGV
    0.06
    iggins
    0.06
    Slug
    0.06
    Activations Density 0.003%

    No Known Activations