© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 124824
    Prev
    Next
    INDEX
    Explanations

    occurrences of certain endings or patterns in words, particularly related to measurements and lines of code

    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
    uir
    -0.08
    onna
    -0.08
    оÑĢа
    -0.07
    panion
    -0.07
    juan
    -0.07
    odable
    -0.07
    eroon
    -0.07
    к
    -0.07
    км
    -0.07
    tro
    -0.07
    POSITIVE LOGITS
    mainwindow
    0.06
    /GPL
    0.06
     shr
    0.06
     Sa
    0.06
    contri
    0.05
    buz
    0.05
    EqualityComparer
    0.05
     cul
    0.05
    å¼ı
    0.05
     memor
    0.05
    Activations Density 0.000%

    No Known Activations