© 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. 107890
    Prev
    Next
    INDEX
    Explanations

    mentions of endangered species and their habitats

    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
     mut
    -0.07
     polar
    -0.06
    wie
    -0.06
    otime
    -0.06
    heimer
    -0.06
    eteria
    -0.06
     polo
    -0.06
    諸
    -0.06
     lam
    -0.05
     asiat
    -0.05
    POSITIVE LOGITS
    adero
    0.08
     locations
    0.08
    osy
    0.07
    ocos
    0.07
     Locations
    0.07
    uffs
    0.07
     sites
    0.07
    iras
    0.07
     tắc
    0.07
     Sites
    0.06
    Activations Density 0.006%

    No Known Activations