© 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. 118890
    Prev
    Next
    INDEX
    Explanations

    statistical values and results related to medical 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
    rades
    -0.07
    659
    -0.06
    kul
    -0.06
    RAR
    -0.06
     buggy
    -0.06
    uluk
    -0.06
    reso
    -0.06
    ãĥĨãĥ«
    -0.06
    ODB
    -0.06
    oord
    -0.06
    POSITIVE LOGITS
    imir
    0.07
    ipl
    0.07
     Muss
    0.06
    оди
    0.06
    ãĥªãĥ¼
    0.06
    imat
    0.06
    393
    0.06
    飯
    0.06
    à¥Ģब
    0.06
     twice
    0.06
    Activations Density 0.010%

    No Known Activations