© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 125142
    Prev
    Next
    INDEX
    Explanations

    phrases describing instability or uncertainty in life

    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
    cke
    -0.06
     somehow
    -0.06
    ìĤ¬ë¬´
    -0.06
    ampa
    -0.06
    719
    -0.05
    edula
    -0.05
     Naturally
    -0.05
    èĪŀ
    -0.05
    áºŃu
    -0.05
    chron
    -0.05
    POSITIVE LOGITS
     anytime
    0.15
     sudden
    0.12
     instant
    0.12
     any
    0.10
     ìĸ¸ìłľ
    0.10
     kdy
    0.10
    éļ¨
    0.10
    éļı
    0.10
    çªģçĦ¶
    0.09
    æŦ
    0.09
    Activations Density 0.156%

    No Known Activations