© 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. 73232
    Prev
    Next
    INDEX
    Explanations

    trends related to narrative style and character development in writing

    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
    510
    -0.06
    iron
    -0.06
     leaf
    -0.06
     fucking
    -0.05
     Fuck
    -0.05
    854
    -0.05
     fork
    -0.05
    -X
    -0.05
     —
    -0.05
     Leaf
    -0.05
    POSITIVE LOGITS
    ÑĢаÑħов
    0.07
    TRACE
    0.07
     Чи
    0.07
    .CommandType
    0.07
     readers
    0.07
    åĴ¨
    0.07
    ittle
    0.07
     aras
    0.07
     prostitut
    0.07
    riter
    0.07
    Activations Density 0.000%

    No Known Activations