© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 29379
    Prev
    Next
    INDEX
    Explanations

    concepts related to resilience and natural phenomena

    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
    swick
    -0.07
     associate
    -0.06
     Associate
    -0.06
     Assoc
    -0.06
    anj
    -0.06
    eness
    -0.06
     Bless
    -0.06
    ÑĪев
    -0.06
     Alman
    -0.06
    udge
    -0.06
    POSITIVE LOGITS
    ê·¹
    0.06
    atab
    0.06
    :async
    0.06
    agger
    0.06
    pard
    0.06
    494
    0.06
    à¹Ħà¸ĭ
    0.06
    -sale
    0.06
     ETA
    0.06
    ë°°
    0.06
    Activations Density 0.134%

    No Known Activations