© 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. 842
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate avoidance or prevention of problems

    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
    áº
    -0.08
    ecko
    -0.07
    ë¨
    -0.07
    /TT
    -0.07
     serialVersionUID
    -0.07
    Äįet
    -0.07
    .kr
    -0.07
    empo
    -0.07
    pdata
    -0.07
    íĨłíĨł
    -0.07
    POSITIVE LOGITS
     need
    0.08
    /mit
    0.07
     most
    0.07
    LayoutInflater
    0.07
     Ñģобой
    0.06
     concern
    0.06
     concerns
    0.06
     inter
    0.06
     opportunities
    0.06
     Need
    0.06
    Activations Density 0.017%

    No Known Activations