© 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. 9-LLAMASCOPE-RES-131K
    11. 98266
    Prev
    Next
    INDEX
    Explanations

    references to insulin and its related 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
    ht
    -0.07
    inka
    -0.07
    rego
    -0.07
    ourg
    -0.07
    rif
    -0.07
    hti
    -0.07
    fcc
    -0.07
    ibre
    -0.07
    ufe
    -0.07
    stadt
    -0.07
    POSITIVE LOGITS
    veis
    0.06
     noqa
    0.06
    ëĵĿ
    0.06
     Jenkins
    0.06
    BJ
    0.06
    827
    0.06
    æ¨
    0.06
    (hand
    0.05
    VERR
    0.05
    ī
    0.05
    Activations Density 0.001%

    No Known Activations