© 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. 4514
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate the identification and discussion of problems or challenges

    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
    ungle
    -0.09
    /GL
    -0.08
     ydk
    -0.08
    ampo
    -0.07
    ancode
    -0.07
    ¤í
    -0.07
    EventData
    -0.07
    /Gate
    -0.07
    RowCount
    -0.07
    anship
    -0.07
    POSITIVE LOGITS
     needs
    0.09
     concerns
    0.08
     specific
    0.07
     gaps
    0.07
    ch
    0.07
    ign
    0.06
    isol
    0.06
    needs
    0.06
     demand
    0.06
     Needs
    0.06
    Activations Density 0.018%

    No Known Activations