© 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. 3543
    Prev
    Next
    INDEX
    Explanations

    brands and their mentions 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
    ERRU
    -0.07
     authDomain
    -0.07
    :;"
    -0.07
    Uvs
    -0.07
    URLException
    -0.07
     geile
    -0.07
    :`~
    -0.07
    \Console
    -0.06
    PointSize
    -0.06
     NotImplemented
    -0.06
    POSITIVE LOGITS
    's
    0.09
     itself
    0.08
    ’s
    0.08
     own
    0.07
    âĢ¦↵↵↵
    0.07
    èĩªèº«
    0.06
    undy
    0.06
     âĩ
    0.06
     himself
    0.06
    amedi
    0.06
    Activations Density 0.036%

    No Known Activations