© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 88297
    Prev
    Next
    INDEX
    Explanations

    comments or annotations within code, typically signifying documentation or summaries for methods and classes

    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
    ãģ°ãģĭãĤĬ
    -0.06
    mae
    -0.06
    ÑĤаб
    -0.06
    alan
    -0.06
    å¼¥
    -0.06
    /bit
    -0.06
     occult
    -0.06
    ses
    -0.06
    .managed
    -0.06
    ooth
    -0.06
    POSITIVE LOGITS
    eÄį
    0.07
    DST
    0.07
    Å¡il
    0.07
     bytesRead
    0.07
    bsolute
    0.07
    erator
    0.07
    -fontawesome
    0.07
    iyel
    0.07
     arsch
    0.07
    ï¸
    0.07
    Activations Density 0.004%

    No Known Activations