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. 43405
    Prev
    Next
    INDEX
    Explanations

    terms related to obstructive sleep apnea

    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
    innen
    -0.07
    eh
    -0.07
    lingen
    -0.06
    ingham
    -0.06
    lings
    -0.06
    iben
    -0.06
    umlu
    -0.06
     Kraft
    -0.06
    IGN
    -0.06
    ef
    -0.06
    POSITIVE LOGITS
    nea
    0.22
    neas
    0.15
    ena
    0.12
    obia
    0.12
    nia
    0.11
    pliance
    0.11
    enia
    0.11
    ria
    0.10
    athy
    0.10
    no
    0.10
    Activations Density 0.004%

    No Known Activations