© 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. 29706
    Prev
    Next
    INDEX
    Explanations

    questions and phrases involving the word "who."

    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
    Expose
    -0.07
     teb
    -0.06
    kovi
    -0.06
    cke
    -0.06
    inox
    -0.06
     herself
    -0.06
    _equals
    -0.06
    >"+↵
    -0.06
     selv
    -0.06
    à¹Ģà¸Ńà¸ĩ
    -0.06
    POSITIVE LOGITS
     responsibility
    0.08
    -scrollbar
    0.07
     Responsibility
    0.07
    лаÑĪ
    0.07
    emony
    0.06
     Ø¢ÛĮا
    0.06
     ultimately
    0.06
    Respons
    0.06
     комÑĥ
    0.06
    âĶģâĶģâĶģâĶģâĶģâĶģâĶģâĶģâĶģâĶģâĶģâĶģâĶģâĶģâĶģâĶģ
    0.06
    Activations Density 0.010%

    No Known Activations