© 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. 42024
    Prev
    Next
    INDEX
    Explanations

    phrases related to cycles and self-fulfilling prophecies

    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
    chner
    -0.07
     nad
    -0.06
     tek
    -0.06
    omid
    -0.06
    _unregister
    -0.06
    esar
    -0.06
     patch
    -0.05
     Sever
    -0.05
    ãĥĥãĥĦ
    -0.05
     Pic
    -0.05
    POSITIVE LOGITS
    loop
    0.20
     loop
    0.19
    循
    0.18
     Loop
    0.17
    LOOP
    0.17
     circular
    0.17
     cycle
    0.17
    Loop
    0.17
     loops
    0.17
     circle
    0.16
    Activations Density 0.156%

    No Known Activations