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

    Neuronpedia

    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. 17-LLAMASCOPE-RES-131K
    11. 77733
    Prev
    Next
    INDEX
    Explanations

    technical parameters and attributes in code-related contexts

    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
     ìŀĪê³ł
    -0.09
    .scalablytyped
    -0.08
    ìĿ´ê³ł
    -0.07
    ãģ§ãģĤãĤĬ
    -0.07
    ogonal
    -0.07
    ãĢģ
    -0.07
    regunta
    -0.07
    essel
    -0.07
    ullen
    -0.06
    ucas
    -0.06
    POSITIVE LOGITS
    (optional
    0.08
     respectively
    0.07
     alike
    0.07
    eteria
    0.07
     ÑģооÑĤвеÑĤ
    0.07
    ÐIJÑĢÑħÑĸв
    0.06
    쳤ëĭ¤
    0.06
    ترÛĮ
    0.06
     ']
    0.06
     Eck
    0.06
    Activations Density 0.074%

    No Known Activations