© 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. 106587
    Prev
    Next
    INDEX
    Explanations

    achievements and qualifications in education and professional 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
    anka
    -0.07
    anou
    -0.07
    adu
    -0.07
    анка
    -0.07
    mk
    -0.07
    bang
    -0.06
    antity
    -0.06
    éf
    -0.06
    angan
    -0.06
    ENUM
    -0.06
    POSITIVE LOGITS
    agna
    0.06
     rec
    0.06
     student
    0.06
     finishing
    0.06
     finish
    0.06
     Exped
    0.06
     Student
    0.06
     graduating
    0.06
     pole
    0.06
    ational
    0.06
    Activations Density 0.018%

    No Known Activations