© 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. 1735
    Prev
    Next
    INDEX
    Explanations

    references to time, specifically the concept of "week."

    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
    kip
    -0.07
    Enlarge
    -0.06
    ylko
    -0.06
     Levitra
    -0.05
    oppers
    -0.05
     å¿
    -0.05
    IEL
    -0.05
    chrome
    -0.05
     âĹĨ
    -0.05
     Nobel
    -0.05
    POSITIVE LOGITS
    achment
    0.07
    agos
    0.07
     Yun
    0.07
    ltr
    0.07
    asers
    0.07
    '])?
    0.06
    ichel
    0.06
    asi
    0.06
    ohl
    0.06
    alten
    0.06
    Activations Density 0.000%

    No Known Activations