© 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. 16012
    Prev
    Next
    INDEX
    Explanations

    code related to vector and geometric constructs

    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
    -det
    -0.07
    -Sah
    -0.07
     |--------------------------------------------------------------------------↵
    -0.07
    znik
    -0.06
     Mant
    -0.06
    itung
    -0.06
     suce
    -0.06
    Ïĥμα
    -0.06
    ByVersion
    -0.06
    çħ
    -0.06
    POSITIVE LOGITS
    /gtest
    0.06
    antis
    0.06
    0.06
     tether
    0.06
     manually
    0.06
    tes
    0.06
    PMC
    0.06
     manual
    0.06
    assin
    0.05
     ging
    0.05
    Activations Density 0.056%

    No Known Activations