© 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. 3734
    Prev
    Next
    INDEX
    Explanations

    names and terms associated with various businesses and organizations

    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
     -*-č↵
    -0.09
     огÑĢа
    -0.09
    Äįel
    -0.08
    IXEL
    -0.07
    /*č↵
    -0.07
     Hük
    -0.07
    ÑİÑĢ
    -0.07
    ULE
    -0.07
    ARAM
    -0.07
    ÙĪزÙĩ
    -0.07
    POSITIVE LOGITS
     Group
    0.08
    Group
    0.08
    ye
    0.06
    252
    0.06
    oe
    0.06
    elf
    0.06
     group
    0.06
     GROUP
    0.06
    eto
    0.06
    owing
    0.06
    Activations Density 0.016%

    No Known Activations