© 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. 9-LLAMASCOPE-RES-131K
    11. 97409
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Updated" with varying timestamp formats

    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
    ervo
    -0.06
    erv
    -0.06
    лем
    -0.06
    erview
    -0.06
    eria
    -0.06
     envelope
    -0.05
    ÄĽÅ¾
    -0.05
    alo
    -0.05
    opak
    -0.05
    wise
    -0.05
    POSITIVE LOGITS
     Ulus
    0.08
    reopen
    0.08
    stasy
    0.07
    YNAM
    0.07
    olatile
    0.07
    yny
    0.07
    .plist
    0.07
    LOCKS
    0.07
    _rg
    0.07
    mente
    0.07
    Activations Density 0.008%

    No Known Activations