© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 29589
    Prev
    Next
    INDEX
    Explanations

    terms related to medical procedures and disposal methods for hazardous materials

    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
    tring
    -0.07
    arine
    -0.07
    IBC
    -0.07
     ApiController
    -0.07
     Helm
    -0.07
    æŀ
    -0.07
    DEM
    -0.06
    crete
    -0.06
    pector
    -0.06
    \TestCase
    -0.06
    POSITIVE LOGITS
     needle
    0.11
    needle
    0.10
     needles
    0.09
     tip
    0.08
     Needle
    0.08
     stabbed
    0.08
    stab
    0.07
     inserted
    0.07
     shaft
    0.07
     stabbing
    0.07
    Activations Density 0.026%

    No Known Activations