© 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. 73918
    Prev
    Next
    INDEX
    Explanations

    references to language learning opportunities and programs

    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
    ags
    -0.07
    شار
    -0.07
    uries
    -0.07
     synonyms
    -0.07
    adera
    -0.07
    ieee
    -0.07
    enburg
    -0.07
    uma
    -0.06
     Thr
    -0.06
    ury
    -0.06
    POSITIVE LOGITS
     Foreign
    0.10
     foreign
    0.09
     language
    0.09
     acquisition
    0.09
     Acquisition
    0.09
    -learning
    0.08
     FOREIGN
    0.08
     Imper
    0.08
    Foreign
    0.08
     Languages
    0.07
    Activations Density 0.067%

    No Known Activations