© 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. 61084
    Prev
    Next
    INDEX
    Explanations

    occurrences of the name "Scho" in various contexts

    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
    ugin
    -0.07
    à¥Ģय
    -0.06
    Ưá»
    -0.06
    xed
    -0.06
    ugi
    -0.06
    POOL
    -0.06
    äs
    -0.06
    ç½®
    -0.06
    sei
    -0.06
    æĺİ
    -0.06
    POSITIVE LOGITS
    emaker
    0.07
    ORMAT
    0.07
    lift
    0.07
    enville
    0.07
    ory
    0.07
     ÐIJнд
    0.07
    ie
    0.07
    craft
    0.07
    ester
    0.07
    girls
    0.06
    Activations Density 0.008%

    No Known Activations