© 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. 125266
    Prev
    Next
    INDEX
    Explanations

    corporate strategies and investment opportunities

    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
    ustos
    -0.07
    IDL
    -0.06
    upil
    -0.06
    iyah
    -0.06
     spell
    -0.06
    gz
    -0.06
    igg
    -0.06
    swick
    -0.06
    iosa
    -0.06
    egend
    -0.05
    POSITIVE LOGITS
    %C
    0.07
    liqu
    0.07
     runway
    0.07
    antaged
    0.06
     Operators
    0.06
    odem
    0.06
     گردÛĮد
    0.06
    atab
    0.06
    à¥Ĥà¤ģ
    0.06
    jad
    0.06
    Activations Density 0.016%

    No Known Activations