© 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. 98424
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the concept of "with" in various contexts

    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
    iah
    -0.08
    oplevel
    -0.07
    yle
    -0.07
    ahn
    -0.07
    ona
    -0.06
    ucher
    -0.06
    icopt
    -0.06
    roken
    -0.06
    roperty
    -0.06
    rio
    -0.06
    POSITIVE LOGITS
    .Ui
    0.07
    OMPI
    0.07
     Klo
    0.07
    ütün
    0.06
     prive
    0.06
    ستÛĮ
    0.06
    bid
    0.06
    warz
    0.06
    JI
    0.06
    OLA
    0.06
    Activations Density 0.025%

    No Known Activations