© 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. 3759
    Prev
    Next
    INDEX
    Explanations

    statements expressing personal opinions and self-reflection

    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
    olk
    -0.09
    portun
    -0.07
    asons
    -0.07
    ismu
    -0.07
    outu
    -0.07
    elay
    -0.07
    icari
    -0.07
     lẽ
    -0.07
    ActivityIndicatorView
    -0.07
    OPY
    -0.07
    POSITIVE LOGITS
     but
    0.11
     nor
    0.09
     pero
    0.07
     nhÆ°ng
    0.06
     αλλά
    0.06
    but
    0.06
    æ´²
    0.06
     (?)
    0.05
    153
    0.05
     gene
    0.05
    Activations Density 0.021%

    No Known Activations