© 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. 107540
    Prev
    Next
    INDEX
    Explanations

    programming concepts and technical details related to data management and server connections

    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
     unlike
    -0.09
     beyond
    -0.07
     compared
    -0.07
    ãģĿãģĹãģ¦
    -0.07
     among
    -0.06
    ded
    -0.06
    aga
    -0.06
     amongst
    -0.06
    gia
    -0.06
    Beyond
    -0.06
    POSITIVE LOGITS
     instead
    0.26
    instead
    0.23
     Instead
    0.20
    Instead
    0.18
     вмеÑģÑĤ
    0.15
    à¹ģà¸Ĺà¸Ļ
    0.14
    代
    0.10
     naopak
    0.09
     代
    0.09
    ãģ»ãģĨ
    0.09
    Activations Density 0.098%

    No Known Activations