© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 121621
    Prev
    Next
    INDEX
    Explanations

    CSS styling attributes and their values in code snippets

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    ↵
    -0.06
    itz
    -0.06
    irt
    -0.06
    Âł
    -0.06
     way
    -0.05
    925
    -0.05
     Sul
    -0.05
     om
    -0.05
     z
    -0.05
    âĢ¦↵
    -0.05
    POSITIVE LOGITS
    erif
    0.10
     konkrét
    0.09
    imdi
    0.09
    onec
    0.09
    ãĥĨãĥ«
    0.08
    ınca
    0.08
    аÑĢÑĩ
    0.08
    imizde
    0.08
     addCriterion
    0.08
    _bullet
    0.08
    Activations Density 0.007%

    No Known Activations