© 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. 93964
    Prev
    Next
    INDEX
    Explanations

    references to awards related to excellence in education and children's literature

    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
    è£
    -0.07
    ÑĪев
    -0.07
     ^{°}
    -0.07
    ÃŃrk
    -0.07
    vic
    -0.07
    eses
    -0.07
     æĺŁ
    -0.07
    upal
    -0.06
    ffects
    -0.06
     tô
    -0.06
    POSITIVE LOGITS
    ÑĢиÑĦ
    0.07
    ayette
    0.07
    CHANT
    0.06
     craftsmanship
    0.06
    egg
    0.06
    orsch
    0.06
    ilip
    0.06
    ÑĢап
    0.06
     Broadcasting
    0.06
    anch
    0.06
    Activations Density 0.004%

    No Known Activations