© 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. 61268
    Prev
    Next
    INDEX
    Explanations

    specific genes and their functions related to cancer and genetic mutations

    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
    CCI
    -0.08
    tridge
    -0.08
    TERS
    -0.08
    atta
    -0.08
    illance
    -0.08
    bine
    -0.07
    dong
    -0.07
    пÑĢиклад
    -0.07
    ÙĨاÙĨ
    -0.07
    -urlencoded
    -0.07
    POSITIVE LOGITS
     genes
    0.08
     proteins
    0.07
    ispens
    0.06
     Y
    0.06
     protein
    0.06
     dispens
    0.06
     ÑĢеÑĨеп
    0.06
     knock
    0.06
     enzymes
    0.06
    زد
    0.05
    Activations Density 0.121%

    No Known Activations