© 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. 3654
    Prev
    Next
    INDEX
    Explanations

    variations of the word "theme" in different 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
    roj
    -0.07
    áy
    -0.07
    EFA
    -0.07
    aleza
    -0.07
    svp
    -0.07
    ỡ
    -0.07
    sponsor
    -0.07
    onda
    -0.06
     Paginator
    -0.06
    _membership
    -0.06
    POSITIVE LOGITS
     Th
    0.08
    essen
    0.08
    elen
    0.06
    maz
    0.06
    eler
    0.06
    za
    0.06
    ickers
    0.06
    åħ±åĴĮ
    0.06
    aza
    0.06
    же
    0.06
    Activations Density 0.007%

    No Known Activations