© 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. 106615
    Prev
    Next
    INDEX
    Explanations

    numerical data and financial figures

    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
    uzzi
    -0.07
    nostic
    -0.06
    Å«
    -0.06
    ickle
    -0.06
     herb
    -0.06
    coni
    -0.06
     createStackNavigator
    -0.06
     Kurul
    -0.06
    WK
    -0.06
    اÙĨÙĬØ©
    -0.06
    POSITIVE LOGITS
    اث
    0.07
    ideon
    0.06
    ç´ł
    0.06
    obi
    0.06
    630
    0.06
    ensch
    0.06
    ubb
    0.06
    νÏİ
    0.06
     AsyncCallback
    0.06
     six
    0.06
    Activations Density 0.014%

    No Known Activations