© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 3720
    Prev
    Next
    INDEX
    Explanations

    references to individuals and their relationships

    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
    hled
    -0.09
    osg
    -0.09
    ñana
    -0.09
    annies
    -0.08
    okino
    -0.08
    emek
    -0.08
    ©©
    -0.08
    -------------</
    -0.08
    ibu
    -0.08
    ----------</
    -0.08
    POSITIVE LOGITS
     employers
    0.08
     former
    0.08
     supporters
    0.08
     owner
    0.07
     parents
    0.07
     owners
    0.07
     handler
    0.07
     des
    0.07
     fans
    0.07
     admir
    0.07
    Activations Density 0.038%

    No Known Activations