© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 125007
    Prev
    Next
    INDEX
    Explanations

    references to music or literary works, particularly highlighting notable characteristics and their creators

    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
     Whe
    -0.07
     curvature
    -0.06
     vale
    -0.06
     whe
    -0.06
    Trace
    -0.06
    ána
    -0.06
     Yosh
    -0.06
     Merk
    -0.06
     Slav
    -0.06
    OTAL
    -0.06
    POSITIVE LOGITS
     untranslated
    0.11
     translated
    0.11
     translation
    0.09
     Translation
    0.09
    translated
    0.08
     translations
    0.08
     translates
    0.08
     translate
    0.08
     bilingual
    0.08
    translation
    0.08
    Activations Density 0.064%

    No Known Activations