© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 59729
    Prev
    Next
    INDEX
    Explanations

    roles and titles related to academic students and candidates

    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
    licos
    -0.07
    ocations
    -0.07
    infeld
    -0.07
    anders
    -0.07
    дем
    -0.06
    Adult
    -0.06
    ãĥ«ãĥķ
    -0.06
    Runnable
    -0.06
    ocab
    -0.06
    elsea
    -0.06
    POSITIVE LOGITS
    ogo
    0.07
    /post
    0.07
     ort
    0.06
     جر
    0.06
     studying
    0.06
     autogenerated
    0.06
    328
    0.06
    ago
    0.06
    otion
    0.05
     chez
    0.05
    Activations Density 0.013%

    No Known Activations