© 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. 88107
    Prev
    Next
    INDEX
    Explanations

    categories and concepts related to biological and diversity frameworks

    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
    ylko
    -0.08
    gili
    -0.08
    abar
    -0.08
    VERRIDE
    -0.07
    erras
    -0.07
    سÙĩ
    -0.07
    .fd
    -0.07
     VÅ¡ech
    -0.07
    crets
    -0.07
    eah
    -0.07
    POSITIVE LOGITS
     &
    0.08
     ans
    0.06
    &
    0.06
    920
    0.06
    _inches
    0.06
     and
    0.05
    740
    0.05
    ìĹ´
    0.05
     Petite
    0.05
    741
    0.05
    Activations Density 0.041%

    No Known Activations