© 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. 58179
    Prev
    Next
    INDEX
    Explanations

    key features and mechanics of slot games

    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
    anka
    -0.06
     Shank
    -0.06
     Wire
    -0.06
    liner
    -0.06
    zu
    -0.06
    langs
    -0.06
    545
    -0.06
     jo
    -0.06
     Hanna
    -0.05
     ÐĹаÑħ
    -0.05
    POSITIVE LOGITS
    Introduced
    0.07
    asti
    0.07
    ìĿ´ìĬ¤
    0.07
    .jquery
    0.07
     Introduced
    0.07
    åħ¼
    0.07
     WCHAR
    0.07
    (æ°´
    0.06
    uestos
    0.06
    _library
    0.06
    Activations Density 0.008%

    No Known Activations