© 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. 72744
    Prev
    Next
    INDEX
    Explanations

    phrases related to hope and future aspirations

    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
    akra
    -0.07
    ipes
    -0.06
    untime
    -0.06
    rogate
    -0.06
    нг
    -0.06
    urring
    -0.06
    दर
    -0.06
    leme
    -0.06
    leon
    -0.06
    лив
    -0.06
    POSITIVE LOGITS
     future
    0.12
     further
    0.10
    future
    0.09
     weiter
    0.09
     continue
    0.09
     tomorrow
    0.09
     past
    0.08
     continuation
    0.08
     continued
    0.08
     weitere
    0.08
    Activations Density 0.023%

    No Known Activations