© 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. 82387
    Prev
    Next
    INDEX
    Explanations

    statements about the existence or characteristics of subjects

    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
    ámara
    -0.08
    ноп
    -0.08
     wed
    -0.08
    .Loader
    -0.07
    ezi
    -0.07
    ards
    -0.07
    icks
    -0.07
    TEGER
    -0.07
    TouchEvent
    -0.07
    ázev
    -0.07
    POSITIVE LOGITS
    :
    0.07
     اÛĮÙĨÚ©Ùĩ
    0.06
    963
    0.06
    0.06
    /is
    0.06
    oling
    0.06
    bor
    0.06
    abelle
    0.06
     to
    0.06
     none
    0.05
    Activations Density 0.019%

    No Known Activations