© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 40638
    Prev
    Next
    INDEX
    Explanations

    medical and academic affiliations related to healthcare

    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
    /Instruction
    -0.07
    åłĤ
    -0.06
    sty
    -0.06
    lsi
    -0.06
    UDA
    -0.06
    xdf
    -0.06
    usize
    -0.06
     tableLayoutPanel
    -0.06
     znam
    -0.06
    orie
    -0.06
    POSITIVE LOGITS
     à¹Ĥรà¸ĩ
    0.08
     Hospital
    0.07
    ilon
    0.07
    etty
    0.06
     facilities
    0.06
    Ìĥ
    0.06
    æĮĤ
    0.06
     treating
    0.06
    Hospital
    0.06
     hops
    0.06
    Activations Density 0.040%

    No Known Activations