© 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. 31314
    Prev
    Next
    INDEX
    Explanations

    dates and time-related expressions

    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
     Patterson
    -0.06
    inz
    -0.06
    jay
    -0.05
     Murdoch
    -0.05
    edBy
    -0.05
    yz
    -0.05
    ATTERN
    -0.05
    esel
    -0.05
    ez
    -0.05
     carving
    -0.05
    POSITIVE LOGITS
    ropa
    0.09
    POOL
    0.08
     McInt
    0.07
    hoo
    0.07
     theor
    0.07
    /Sub
    0.07
    upos
    0.07
    pio
    0.07
    noÅĽÄĩ
    0.07
    engu
    0.07
    Activations Density 0.013%

    No Known Activations