© 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 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. 74976
    Prev
    Next
    INDEX
    Explanations

    academic and professional recognition awards in the context of education and research

    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
    ãģĿãģĹãģ¦
    -0.09
     ê·¸ë¦¬ê³ł
    -0.08
    ãĢĤãģĿãģĹãģ¦
    -0.08
    zar
    -0.06
    erp
    -0.06
    eri
    -0.06
    ÂĢ
    -0.06
    entr
    -0.06
    .opensource
    -0.06
    .combine
    -0.06
    POSITIVE LOGITS
    ILLS
    0.08
    retval
    0.07
    :
    0.07
    visor
    0.07
    verages
    0.07
    criptor
    0.07
    iples
    0.06
    θμ
    0.06
    ÑĮÑİ
    0.06
    ứng
    0.06
    Activations Density 0.036%

    No Known Activations