© 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. 76482
    Prev
    Next
    INDEX
    Explanations

    references to philosophical concepts and figures

    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
    pesan
    -0.07
     propri
    -0.06
    ushman
    -0.06
    ãĥ³ãĥĶ
    -0.06
     Grape
    -0.06
     subur
    -0.06
    EventData
    -0.06
     pros
    -0.06
     Matth
    -0.06
    rocket
    -0.06
    POSITIVE LOGITS
     philosopher
    0.09
     Philosophy
    0.08
     philosophy
    0.08
     philosophers
    0.08
     ÙģÙĦس
    0.08
     Umb
    0.08
     philosophical
    0.07
    ÏĨι
    0.07
    phil
    0.07
    osopher
    0.07
    Activations Density 0.306%

    No Known Activations