© 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. 26902
    Prev
    Next
    INDEX
    Explanations

    references to live streaming events and online broadcasting

    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
    uls
    -0.06
    '
    -0.06
     next
    -0.06
     within
    -0.06
    -0.05
     male
    -0.05
    M
    -0.05
     competitive
    -0.05
     adult
    -0.05
    vr
    -0.05
    POSITIVE LOGITS
    .idea
    0.09
    .scal
    0.09
    ]âĢı
    0.08
    аÑĢÑħ
    0.07
    ↵↵
    0.07
     Verfüg
    0.07
    coverage
    0.07
     lô
    0.07
    _drvdata
    0.07
    Hour
    0.07
    Activations Density 0.012%

    No Known Activations