© 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. 3563
    Prev
    Next
    INDEX
    Explanations

    medical conditions affecting animals

    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
    lass
    -0.07
    lok
    -0.06
    avs
    -0.06
    quo
    -0.06
    quier
    -0.06
    avl
    -0.06
    suma
    -0.06
    درÛĮ
    -0.06
    lest
    -0.06
     productivity
    -0.06
    POSITIVE LOGITS
     weakened
    0.08
     predis
    0.07
     weaken
    0.07
     exposure
    0.07
     Exposure
    0.07
     suscept
    0.07
     exposed
    0.07
     susceptible
    0.07
     urban
    0.06
     exposures
    0.06
    Activations Density 0.039%

    No Known Activations