© 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. 76763
    Prev
    Next
    INDEX
    Explanations

    instances of significant dates or numerical values in a text

    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
    onse
    -0.07
     Pike
    -0.07
    ÑĢава
    -0.07
     gó
    -0.07
     Surveillance
    -0.07
     graft
    -0.07
    ény
    -0.07
    jde
    -0.07
    unsch
    -0.07
     Anniversary
    -0.07
    POSITIVE LOGITS
    anded
    0.06
     Kurum
    0.06
    590
    0.06
    od
    0.06
    olest
    0.06
     getTitle
    0.05
    optimized
    0.05
    obuf
    0.05
    uede
    0.05
    ê¶Į
    0.05
    Activations Density 0.003%

    No Known Activations