© 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. 125391
    Prev
    Next
    INDEX
    Explanations

    terms related to medical treatments and vitamin supplementation

    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
     kia
    -0.07
    rous
    -0.07
    uitka
    -0.07
    åIJIJ
    -0.06
    isia
    -0.06
    ÅĤÄħ
    -0.06
    mach
    -0.06
    Indent
    -0.06
    inder
    -0.06
    piring
    -0.06
    POSITIVE LOGITS
     administrations
    0.08
     dos
    0.08
     boost
    0.08
     doses
    0.07
     intervention
    0.07
    .done
    0.07
     dose
    0.07
     applied
    0.07
    опÑĢи
    0.07
     подк
    0.07
    Activations Density 0.096%

    No Known Activations