© 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. 74392
    Prev
    Next
    INDEX
    Explanations

    phrases related to balance and stability 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
    chez
    -0.08
    zzo
    -0.07
    otts
    -0.07
    AllWindows
    -0.07
    quist
    -0.07
    luv
    -0.07
    ONO
    -0.07
    illez
    -0.07
    osl
    -0.07
    flen
    -0.06
    POSITIVE LOGITS
     balance
    0.16
     Balance
    0.15
    balance
    0.14
     balances
    0.13
     stability
    0.13
     balancing
    0.13
     balanced
    0.12
    Balance
    0.12
     unstable
    0.12
     Stability
    0.11
    Activations Density 0.020%

    No Known Activations