© 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. 1884
    Prev
    Next
    INDEX
    Explanations

    references to HTML and web development concepts

    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
    Ngh
    -0.07
    792
    -0.07
    culus
    -0.07
     éĤ
    -0.07
     xa
    -0.06
    è¾
    -0.06
    å¯
    -0.06
    682
    -0.06
    chants
    -0.06
    ůj
    -0.06
    POSITIVE LOGITS
    елÑİ
    0.07
    ase
    0.06
     Pole
    0.06
     herk
    0.06
    usto
    0.06
    stant
    0.06
    گاÙĨ
    0.06
    _Impl
    0.06
    æ´Ĺ
    0.06
     Rin
    0.06
    Activations Density 0.001%

    No Known Activations