© 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. 90826
    Prev
    Next
    INDEX
    Explanations

    technical details related to software versioning and platforms

    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
    unden
    -0.06
    ih
    -0.06
     freder
    -0.06
     ÐĴики
    -0.06
    ked
    -0.05
    outers
    -0.05
     clap
    -0.05
     bi
    -0.05
    ayout
    -0.05
    orsi
    -0.05
    POSITIVE LOGITS
    íĮħ
    0.07
    rowsable
    0.07
     target
    0.07
    imd
    0.07
    POCH
    0.07
     Development
    0.07
    -development
    0.07
     Zuk
    0.07
    manifest
    0.07
    development
    0.07
    Activations Density 0.004%

    No Known Activations