© 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. 94715
    Prev
    Next
    INDEX
    Explanations

    patterns related to educational programs and curricular details

    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
    acin
    -0.07
    deen
    -0.07
    å©
    -0.07
    ursed
    -0.07
    antee
    -0.07
    reetings
    -0.07
    etri
    -0.07
    uur
    -0.06
    urent
    -0.06
    urrent
    -0.06
    POSITIVE LOGITS
     extr
    0.07
     club
    0.07
     opportunities
    0.07
     participation
    0.07
     clubs
    0.07
    club
    0.06
     extra
    0.06
     mount
    0.06
    inst
    0.06
     opportun
    0.06
    Activations Density 0.025%

    No Known Activations