© 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. 9-LLAMASCOPE-RES-131K
    11. 96298
    Prev
    Next
    INDEX
    Explanations

    references to design and contests associated with creative projects

    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
     Ham
    -0.06
    itra
    -0.06
    earn
    -0.06
    bia
    -0.06
     Chun
    -0.06
     Che
    -0.06
    utas
    -0.06
    ç¤
    -0.06
    alem
    -0.06
     Tor
    -0.05
    POSITIVE LOGITS
    #
    0.08
     Yön
    0.07
    monds
    0.07
    }elseif
    0.07
    ucht
    0.07
     TObject
    0.07
    KHR
    0.07
    gtest
    0.07
    //{{
    0.07
    usercontent
    0.07
    Activations Density 0.026%

    No Known Activations