© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 84808
    Prev
    Next
    INDEX
    Explanations

    references to prominent musicians and their works

    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
     ><?
    -0.06
    .identity
    -0.06
     meteor
    -0.05
    essa
    -0.05
    λÏį
    -0.05
    lit
    -0.05
    agna
    -0.05
    Dual
    -0.05
    ãģ£ãģį
    -0.05
     means
    -0.05
    POSITIVE LOGITS
     similarly
    0.09
    /Foundation
    0.08
    ä¸Ģæł·
    0.08
    /Instruction
    0.07
    -style
    0.07
    fcn
    0.07
    imilar
    0.07
    ìĿ´ëĤĺ
    0.07
    èĪ¬
    0.07
    gregar
    0.07
    Activations Density 0.022%

    No Known Activations