© 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. 78581
    Prev
    Next
    INDEX
    Explanations

    elements related to disease and research

    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
     covid
    -0.08
    COVID
    -0.07
    ESH
    -0.07
    æ³¥
    -0.07
    avana
    -0.07
    çĽĹ
    -0.07
    ÅĻen
    -0.07
    oud
    -0.07
    é½
    -0.06
    ISTA
    -0.06
    POSITIVE LOGITS
     panic
    0.07
     spreading
    0.07
    rax
    0.06
    Unchecked
    0.06
     spread
    0.06
    unchecked
    0.06
     isolate
    0.06
    panic
    0.06
     viral
    0.06
     fast
    0.06
    Activations Density 0.005%

    No Known Activations