© 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. 86954
    Prev
    Next
    INDEX
    Explanations

    words related to medicinal benefits and properties of substances

    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
    ********************************************************************************
    -0.07
    zen
    -0.07
    ngx
    -0.06
    çĮ
    -0.06
    ós
    -0.06
    URLRequest
    -0.06
    oma
    -0.06
     dek
    -0.06
    .assertThat
    -0.06
    æݪ
    -0.06
    POSITIVE LOGITS
     contains
    0.08
    contains
    0.07
    atin
    0.07
     nature
    0.07
    Contains
    0.07
     properties
    0.07
    oyer
    0.07
     Pun
    0.06
    iali
    0.06
    -bin
    0.06
    Activations Density 0.003%

    No Known Activations