© 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. 77136
    Prev
    Next
    INDEX
    Explanations

    significant interactions and statements of appreciation or acknowledgment

    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
    ourd
    -0.07
    588
    -0.07
    215
    -0.07
    arken
    -0.07
    ãģ£ãģ¨
    -0.07
    óm
    -0.07
    633
    -0.07
    миÑĢ
    -0.07
    umer
    -0.07
    imer
    -0.07
    POSITIVE LOGITS
    ero
    0.06
     chute
    0.06
     Lange
    0.06
     OMX
    0.06
    輪
    0.06
     franca
    0.06
     Candid
    0.06
     Oper
    0.06
    asu
    0.06
    iotic
    0.06
    Activations Density 0.000%

    No Known Activations