© 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 EvalsExportsinterp-engineNEWAPI 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. 54470
    Prev
    Next
    INDEX
    Explanations

    expressions of awareness or understanding of various concepts and situations

    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
    äºĪ
    -0.07
    chan
    -0.07
    коÑĤ
    -0.06
    orman
    -0.06
    hek
    -0.06
    ä¸ĺ
    -0.06
    anax
    -0.06
    par
    -0.06
    asu
    -0.06
    ariance
    -0.06
    POSITIVE LOGITS
     how
    0.10
     presence
    0.07
     Presence
    0.07
    ázd
    0.07
     impending
    0.07
     alternate
    0.07
     danger
    0.07
    etter
    0.07
     dangers
    0.07
    amat
    0.07
    Activations Density 0.012%

    No Known Activations