© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 92258
    Prev
    Next
    INDEX
    Explanations

    references to employment and job-related experiences

    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
    itious
    -0.07
    pants
    -0.07
    redo
    -0.06
    acific
    -0.06
    grab
    -0.06
    inz
    -0.06
    wig
    -0.06
    jÅ¡ÃŃ
    -0.06
    uff
    -0.06
    actory
    -0.06
    POSITIVE LOGITS
    atur
    0.10
    erva
    0.10
    nesota
    0.10
    ãĥ§
    0.10
    /max
    0.09
    nie
    0.09
    ning
    0.09
    neapolis
    0.09
    ogue
    0.09
    erals
    0.08
    Activations Density 0.022%

    No Known Activations