© 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. 85364
    Prev
    Next
    INDEX
    Explanations

    phrases that express the concept of significant amounts or quantities

    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
    emas
    -0.06
    üre
    -0.06
    àµįà´
    -0.06
    uyên
    -0.06
    ento
    -0.06
    æĴĥ
    -0.06
    s
    -0.06
     doch
    -0.06
    aniel
    -0.06
    xes
    -0.06
    POSITIVE LOGITS
    ings
    0.08
    orsi
    0.07
    idelberg
    0.07
    quota
    0.07
    ojis
    0.07
    ownt
    0.07
     amount
    0.07
    ä¹ĭä¸Ģ
    0.07
    .SDK
    0.07
    mah
    0.07
    Activations Density 0.006%

    No Known Activations