© 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. 1731
    Prev
    Next
    INDEX
    Explanations

    phrases relating to limitations and thresholds

    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
    ÙĬراÙĨ
    -0.07
    à¹Īาย
    -0.06
    士
    -0.06
    .jface
    -0.06
    ismet
    -0.06
     Affero
    -0.06
     بÙĩا
    -0.06
    (er
    -0.06
     perpetual
    -0.06
     RH
    -0.06
    POSITIVE LOGITS
     bounds
    0.08
     limits
    0.08
     allotted
    0.07
    æľĢä½³
    0.07
     boundaries
    0.07
     reach
    0.07
    recommended
    0.07
    ensburg
    0.07
     Limits
    0.06
    ائÙģ
    0.06
    Activations Density 0.023%

    No Known Activations