© 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. 78567
    Prev
    Next
    INDEX
    Explanations

    terms related to early detection and intervention in medical contexts

    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
    jen
    -0.07
    older
    -0.07
    ANDING
    -0.06
     dosp
    -0.06
    allo
    -0.06
    OVE
    -0.06
     ileri
    -0.06
    ãĥ¼ãĥ³
    -0.06
    สมà¸ļ
    -0.06
     dol
    -0.06
    POSITIVE LOGITS
     detection
    0.09
    aneously
    0.07
     Detection
    0.07
     intervention
    0.07
    ablish
    0.07
     versus
    0.07
    zeitig
    0.07
    efa
    0.07
    enuity
    0.06
     Intervention
    0.06
    Activations Density 0.010%

    No Known Activations