© 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. 39146
    Prev
    Next
    INDEX
    Explanations

    significant events or outcomes related to internships and career development

    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
    ints
    -0.07
    ÙħÙĨ
    -0.07
    arih
    -0.07
    rah
    -0.07
    ENSITY
    -0.07
    anean
    -0.07
    esModule
    -0.06
     aspect
    -0.06
    XM
    -0.06
    azed
    -0.06
    POSITIVE LOGITS
     being
    0.11
     Being
    0.08
    being
    0.07
    Being
    0.07
    被
    0.07
     sendo
    0.07
     conclusion
    0.07
     overall
    0.07
    owell
    0.06
     被
    0.06
    Activations Density 0.081%

    No Known Activations