© 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 EvalsExportsinterp-engineNEWAPI 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. 54594
    Prev
    Next
    INDEX
    Explanations

    phrases that focus on addressing various issues or problems

    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
    еÑĢеÑĩ
    -0.07
    ic
    -0.07
    umber
    -0.07
    اÙĨÛĮا
    -0.07
     Lever
    -0.06
    oglobin
    -0.06
    ÙģØ´
    -0.06
    Ìģt
    -0.06
     ãĥĵ
    -0.06
    string
    -0.06
    POSITIVE LOGITS
     issues
    0.10
     questions
    0.09
     concerns
    0.09
     issue
    0.08
     Issue
    0.08
    issues
    0.08
    /questions
    0.07
     ìĤ¬íķŃ
    0.07
     needs
    0.07
    /address
    0.07
    Activations Density 0.010%

    No Known Activations