© 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. 58670
    Prev
    Next
    INDEX
    Explanations

    phrases indicating flaws or inadequacies in various contexts

    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
    ano
    -0.06
     inconsistency
    -0.05
    ROUGH
    -0.05
    udes
    -0.05
    论
    -0.05
     vulnerability
    -0.05
    hell
    -0.05
    dep
    -0.05
     tend
    -0.05
     analogue
    -0.05
    POSITIVE LOGITS
     fault
    0.12
     Fault
    0.11
    fault
    0.11
    Fault
    0.09
     intrinsic
    0.09
    trinsic
    0.08
     blame
    0.08
     faults
    0.08
     íĥ
    0.07
    åİŁåĽł
    0.07
    Activations Density 0.048%

    No Known Activations