© 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. 119447
    Prev
    Next
    INDEX
    Explanations

    statements related to floor plans and accommodations

    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
    cer
    -0.06
    strand
    -0.06
    ibold
    -0.06
    âr
    -0.06
    æĿ¾
    -0.06
     failure
    -0.06
     displayed
    -0.05
    ίδα
    -0.05
    anca
    -0.05
     lax
    -0.05
    POSITIVE LOGITS
    ayout
    0.07
    AYOUT
    0.07
     layout
    0.07
     Airways
    0.07
    ç¦
    0.07
    浪
    0.07
     Layout
    0.07
    _LAYOUT
    0.07
    ambre
    0.07
    anela
    0.07
    Activations Density 0.006%

    No Known Activations