© 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. 92572
    Prev
    Next
    INDEX
    Explanations

    phrases indicating ongoing experiences or long-term activities

    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
     earlier
    -0.07
     suddenly
    -0.07
     sudden
    -0.07
     formerly
    -0.07
     etc
    -0.06
     Earlier
    -0.06
    etc
    -0.06
     already
    -0.06
    Earlier
    -0.06
    yny
    -0.05
    POSITIVE LOGITS
     thereafter
    0.17
     subsequently
    0.17
     subsequent
    0.16
    sequently
    0.13
     afterwards
    0.13
     Afterwards
    0.12
     afterward
    0.11
     continued
    0.11
     ìĿ´íĽĦ
    0.11
     ensuite
    0.10
    Activations Density 0.032%

    No Known Activations