© 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. 1889
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to time and duration

    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
    erah
    -0.08
    hurst
    -0.08
    chg
    -0.08
    aken
    -0.07
    anova
    -0.07
    achten
    -0.07
     Dawn
    -0.07
    krom
    -0.07
    haven
    -0.07
    è¦
    -0.06
    POSITIVE LOGITS
     met
    0.07
    s
    0.07
     whole
    0.07
     entire
    0.07
    veis
    0.07
    dess
    0.06
    [OF
    0.06
    ief
    0.06
     cả
    0.06
    ists
    0.06
    Activations Density 0.019%

    No Known Activations