Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 43649
    Prev
    Next
    INDEX
    Explanations

    aspects related to nursing workload and staffing issues

    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
    opak
    -0.06
    dna
    -0.06
     Diseases
    -0.06
     epile
    -0.06
    ONGL
    -0.06
    loff
    -0.06
    thritis
    -0.05
    olk
    -0.05
     Pharmaceuticals
    -0.05
    adlo
    -0.05
    POSITIVE LOGITS
     burn
    0.17
    burn
    0.13
     burned
    0.13
     Burn
    0.12
     burnt
    0.12
    Burn
    0.12
     exhaustion
    0.11
     compassion
    0.10
     burns
    0.10
     burning
    0.10
    Activations Density 0.013%

    No Known Activations