© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 83821
    Prev
    Next
    INDEX
    Explanations

    concepts related to evolution and adaptation in various 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
    tsky
    -0.07
    idot
    -0.06
    ẹn
    -0.06
    ogn
    -0.06
    ohl
    -0.06
    acho
    -0.06
     totiž
    -0.06
    utow
    -0.05
    emey
    -0.05
    illos
    -0.05
    POSITIVE LOGITS
     accordingly
    0.24
     likewise
    0.17
     correspond
    0.17
     Accordingly
    0.16
     ÑģооÑĤвеÑĤ
    0.15
     Likewise
    0.14
     ÑĤоже
    0.13
     corresponding
    0.13
     Correspond
    0.12
     similarly
    0.12
    Activations Density 0.046%

    No Known Activations