© 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. 15-LLAMASCOPE-RES-131K
    11. 89678
    Prev
    Next
    INDEX
    Explanations

    specific dates and notable events in historical 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
    launcher
    -0.08
    #ab
    -0.08
    aeda
    -0.07
     гÑĢн
    -0.07
    ynom
    -0.07
    ież
    -0.07
    ëıĦë¡ľ
    -0.07
    InputElement
    -0.07
    à¥ĭà¤ĸ
    -0.07
    ¯
    -0.07
    POSITIVE LOGITS
    196
    0.07
    197
    0.07
    ilk
    0.06
    194
    0.06
    198
    0.06
    аÑħ
    0.06
    195
    0.06
    inge
    0.06
    itsu
    0.06
    quo
    0.06
    Activations Density 0.031%

    No Known Activations