© 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. 39140
    Prev
    Next
    INDEX
    Explanations

    elements related to motivation and recognition in educational or professional contexts

    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
     rough
    -0.07
     Merc
    -0.06
     fault
    -0.06
    ornings
    -0.06
     sav
    -0.06
    让æĪij
    -0.06
    aison
    -0.06
     sợ
    -0.06
     Mate
    -0.06
     account
    -0.06
    POSITIVE LOGITS
    enze
    0.08
    aroo
    0.07
    ente
    0.07
    eker
    0.07
     Psychology
    0.07
    ULD
    0.07
    ÑĢоÑģÑĤ
    0.06
    jdk
    0.06
     вÑĸ
    0.06
    elage
    0.06
    Activations Density 0.034%

    No Known Activations