© 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. 9-LLAMASCOPE-RES-131K
    11. 94434
    Prev
    Next
    INDEX
    Explanations

    references to timeframes for actions and purchases

    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
    ibu
    -0.07
    alace
    -0.07
    idar
    -0.07
    aldi
    -0.07
    unar
    -0.07
    icer
    -0.07
    OTH
    -0.06
    uld
    -0.06
    viders
    -0.06
    unce
    -0.06
    POSITIVE LOGITS
    oking
    0.06
    ĩ
    0.06
    holm
    0.06
    ãĥ¼ãĥ©
    0.06
    cale
    0.06
    558
    0.06
    .componentInstance
    0.06
    cca
    0.06
    âĦĸâĦĸ
    0.06
    lication
    0.06
    Activations Density 0.028%

    No Known Activations