© 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. 108363
    Prev
    Next
    INDEX
    Explanations

    phrases related to user interactions and comments

    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
    енко
    -0.07
    #ad
    -0.07
    enguin
    -0.07
    ÙĦÙĪد
    -0.06
    ijd
    -0.06
     zas
    -0.06
    .exec
    -0.06
    би
    -0.06
     Kontakt
    -0.06
    bi
    -0.06
    POSITIVE LOGITS
    uais
    0.08
     Disqus
    0.07
     comment
    0.07
     comments
    0.07
    visible
    0.07
    ãĤ³ãĥ¡ãĥ³ãĥĪ
    0.06
     fkk
    0.06
    comments
    0.06
    setVisible
    0.06
    odial
    0.06
    Activations Density 0.023%

    No Known Activations