© 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. 126298
    Prev
    Next
    INDEX
    Explanations

    technical terms and relationships in statistical modeling and data analysis

    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
    IPA
    -0.08
     Vá»ĭ
    -0.07
    ifen
    -0.07
    stanov
    -0.07
    illas
    -0.07
    ocate
    -0.07
    _footer
    -0.06
    .cgi
    -0.06
    otti
    -0.06
    geh
    -0.06
    POSITIVE LOGITS
     variables
    0.10
     Variables
    0.09
    Variables
    0.09
     variable
    0.08
    variables
    0.08
     inputs
    0.08
    ScrollPane
    0.07
    inputs
    0.07
     пеÑĢемен
    0.07
     Variable
    0.07
    Activations Density 0.047%

    No Known Activations