© 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. 124965
    Prev
    Next
    INDEX
    Explanations

    instances of the word "introduction" and its variations

    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
     thù
    -0.07
     spo
    -0.07
    encent
    -0.06
    室
    -0.06
    айд
    -0.06
    reshold
    -0.06
    ıcı
    -0.06
    708
    -0.06
    ÙģضÙĦ
    -0.06
    åĿĤ
    -0.06
    POSITIVE LOGITS
    ductory
    0.08
    iesel
    0.07
    itra
    0.07
    agram
    0.07
    skirts
    0.06
    mates
    0.06
    embers
    0.06
    itom
    0.06
    -END
    0.06
    chein
    0.06
    Activations Density 0.006%

    No Known Activations