© 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. 82983
    Prev
    Next
    INDEX
    Explanations

    key terms related to academic programs and their impacts on education and community engagement

    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
    iya
    -0.07
    .asp
    -0.07
     Gra
    -0.07
    igua
    -0.07
    iyon
    -0.06
    koli
    -0.06
    ximo
    -0.06
    iyah
    -0.06
    him
    -0.06
    elden
    -0.06
    POSITIVE LOGITS
     Thatcher
    0.06
     Leslie
    0.06
    rix
    0.06
     Dire
    0.06
    atrix
    0.06
     Vz
    0.06
    icare
    0.06
     drafts
    0.06
     hemos
    0.06
     sadd
    0.05
    Activations Density 0.038%

    No Known Activations