© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 3230
    Prev
    Next
    INDEX
    Explanations

    statistical measures and values related to diagnostic accuracy

    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
    /cms
    -0.08
    à¥įडल
    -0.07
    _Ptr
    -0.06
    isu
    -0.06
    loy
    -0.06
    gart
    -0.06
    AndPassword
    -0.06
     fortunes
    -0.06
    vil
    -0.06
    QS
    -0.06
    POSITIVE LOGITS
    ÙĪØ¹
    0.08
    ixe
    0.07
    å̼
    0.07
    ê°Ĵ
    0.07
    оÑħ
    0.06
     Fle
    0.06
    uzey
    0.06
     tod
    0.06
    rames
    0.06
    å̤
    0.06
    Activations Density 0.041%

    No Known Activations