Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96205
    Prev
    Next
    INDEX
    Explanations

    technical terms and formal structures in scientific discussions

    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
    ãģıãĤĵ
    -0.06
    __':↵
    -0.06
    GraphNode
    -0.06
    iesz
    -0.06
    ÅĻev
    -0.06
    amen
    -0.06
     \'
    -0.06
    ::__
    -0.06
     åº
    -0.06
    ASI
    -0.06
    POSITIVE LOGITS
    eder
    0.07
     Morr
    0.06
    ÑĮÑİ
    0.06
    Fixed
    0.06
    ithe
    0.06
    voje
    0.06
     FIXED
    0.06
    anton
    0.06
    150
    0.06
    ipop
    0.06
    Activations Density 0.146%

    No Known Activations