© 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. 88565
    Prev
    Next
    INDEX
    Explanations

    messages related to coding conventions and error handling

    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
    our
    -0.06
    Äįi
    -0.06
    lecture
    -0.06
    mental
    -0.06
    assen
    -0.06
    ichtig
    -0.06
    okino
    -0.06
    ManagedObject
    -0.06
    ingo
    -0.06
    ABCDEFGHI
    -0.06
    POSITIVE LOGITS
    gin
    0.06
     sts
    0.06
    atatype
    0.06
     dout
    0.06
    cheng
    0.06
    ernel
    0.06
     Simmons
    0.06
    λÏĮγ
    0.06
    anner
    0.06
     TMPro
    0.06
    Activations Density 0.002%

    No Known Activations