© 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. 124317
    Prev
    Next
    INDEX
    Explanations

    keywords related to date and time functionalities

    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
    onto
    -0.08
    าà¸Ĭ
    -0.08
    orea
    -0.07
    ê³µ
    -0.07
    #.
    -0.06
     muse
    -0.06
    ange
    -0.06
    åĮ
    -0.06
    mé
    -0.06
    kaar
    -0.06
    POSITIVE LOGITS
    !=(
    0.06
    ÑģÑĤиÑĩ
    0.06
    _DRV
    0.06
    ousel
    0.06
    :animated
    0.06
    .'&
    0.06
     Incoming
    0.05
    asso
    0.05
    ä¸ļ
    0.05
    quist
    0.05
    Activations Density 0.003%

    No Known Activations