© 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. 15-LLAMASCOPE-RES-131K
    11. 90088
    Prev
    Next
    INDEX
    Explanations

    technical terms related to 3D graphics or simulation parameters

    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
    à¹Ģà¸ķ
    -0.07
    eam
    -0.06
    .componentInstance
    -0.06
    RuntimeObject
    -0.06
    /lic
    -0.06
     ValidationResult
    -0.06
    HeaderCode
    -0.06
    folio
    -0.06
    overlay
    -0.06
    pend
    -0.06
    POSITIVE LOGITS
    Subview
    0.07
     Eye
    0.07
    iram
    0.06
    :view
    0.06
     view
    0.06
     views
    0.06
     sight
    0.06
    .view
    0.06
     Near
    0.06
     eye
    0.06
    Activations Density 0.028%

    No Known Activations