© 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. 40816
    Prev
    Next
    INDEX
    Explanations

    terms related to medical testing and diagnosis

    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
    NECT
    -0.08
    åĬĩ
    -0.07
     RuntimeObject
    -0.07
    blr
    -0.07
    vertis
    -0.07
    omba
    -0.07
    defgroup
    -0.07
    ough
    -0.07
    pps
    -0.07
    441
    -0.07
    POSITIVE LOGITS
     invent
    0.07
    prov
    0.07
     Rug
    0.06
     tests
    0.06
     checks
    0.06
     Comprehensive
    0.06
     blood
    0.06
    nl
    0.06
     rug
    0.06
    Prov
    0.06
    Activations Density 0.017%

    No Known Activations