© 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 EvalsExportsinterp-engineNEWAPI 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. 18264
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases related to data representation and manipulation

    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
    -addon
    -0.07
    anches
    -0.07
    inis
    -0.07
    ignKey
    -0.06
    ester
    -0.06
    اÙĩرة
    -0.06
    _Interface
    -0.06
    /***/
    -0.06
    ¦
    -0.06
     regul
    -0.06
    POSITIVE LOGITS
     loss
    0.13
     lost
    0.13
    Loss
    0.12
     information
    0.12
     Loss
    0.12
    loss
    0.11
     Lost
    0.11
    Lost
    0.11
     lose
    0.11
    lost
    0.10
    Activations Density 0.119%

    No Known Activations