© 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. 4008
    Prev
    Next
    INDEX
    Explanations

    numerical ratings and scores associated with evaluations

    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
    etime
    -0.06
    adf
    -0.06
     testim
    -0.06
    ubar
    -0.06
     tá»
    -0.06
     اÙĦرسÙħ
    -0.06
     emiss
    -0.06
    402
    -0.06
    elman
    -0.06
    ¬
    -0.05
    POSITIVE LOGITS
    ptune
    0.07
    jee
    0.07
    è¾
    0.07
    è¼
    0.07
     Olson
    0.06
    .fx
    0.06
    ontology
    0.06
    zych
    0.06
    bjerg
    0.06
    inium
    0.06
    Activations Density 0.001%

    No Known Activations