© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 79660
    Prev
    Next
    INDEX
    Explanations

    phrases and idioms related to impending trouble or problematic situations

    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
    .deserialize
    -0.08
    [".
    -0.08
    aison
    -0.07
    Ïģιά
    -0.07
    ùa
    -0.07
    ocab
    -0.07
    lexport
    -0.07
    .lu
    -0.07
    /LICENSE
    -0.07
    iola
    -0.07
    POSITIVE LOGITS
     or
    0.06
     someone
    0.06
     unexpectedly
    0.06
     esp
    0.06
     usu
    0.06
    wert
    0.06
    USTER
    0.05
     oneself
    0.05
     something
    0.05
     situation
    0.05
    Activations Density 0.020%

    No Known Activations