© 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. 2197
    Prev
    Next
    INDEX
    Explanations

    references to technical research or publications

    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
    ederland
    -0.08
    eder
    -0.07
     ÙĦÙĩ
    -0.07
    edges
    -0.07
    ATAB
    -0.07
    ủi
    -0.07
    мп
    -0.07
    кÑĢÑĭ
    -0.07
    ksam
    -0.07
    ÙĤÙĩ
    -0.07
    POSITIVE LOGITS
     bas
    0.07
     vig
    0.07
     Working
    0.07
     Madd
    0.06
     working
    0.06
     res
    0.05
     rig
    0.05
     çķ
    0.05
    -opacity
    0.05
     Tob
    0.05
    Activations Density 0.000%

    No Known Activations