© 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 EvalsExportsAPI 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. 85856
    Prev
    Next
    INDEX
    Explanations

    references to outsourcing 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
    OrDefault
    -0.08
    ücken
    -0.08
    rowse
    -0.08
    zelf
    -0.07
    zin
    -0.07
    ew
    -0.07
    leness
    -0.07
    vanished
    -0.07
    cheng
    -0.07
    -eyed
    -0.07
    POSITIVE LOGITS
    ting
    0.09
    ted
    0.08
    aken
    0.07
    or
    0.07
    =out
    0.07
    /in
    0.07
    ment
    0.07
    stry
    0.07
    myModal
    0.07
    ing
    0.07
    Activations Density 0.002%

    No Known Activations