© 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. 5606
    Prev
    Next
    INDEX
    Explanations

    terms related to phases, parts, and sections in processes or organizational structures

    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
    ↵
    -0.06
    èm
    -0.06
     cross
    -0.06
     hes
    -0.06
     provid
    -0.06
    .lucene
    -0.06
     medical
    -0.06
    лем
    -0.06
     otherwise
    -0.06
     Mast
    -0.05
    POSITIVE LOGITS
    avaÅŁ
    0.07
    urement
    0.07
    ropa
    0.07
    _salt
    0.07
    .scalablytyped
    0.07
    prak
    0.07
     stag
    0.07
    çļĦäºĭ
    0.06
    oeff
    0.06
    ounc
    0.06
    Activations Density 0.012%

    No Known Activations