© 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. 86660
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate neglect or overlooking important details

    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
    иÑĩа
    -0.07
    elor
    -0.07
    locator
    -0.07
    antan
    -0.07
    说çļĦ
    -0.07
    zej
    -0.07
    룬
    -0.07
     nebu
    -0.07
     nackte
    -0.07
    aze
    -0.07
    POSITIVE LOGITS
     altogether
    0.10
     other
    0.09
     how
    0.07
     crucial
    0.07
     important
    0.07
     real
    0.07
     consideration
    0.07
     actually
    0.07
     completely
    0.07
     fact
    0.07
    Activations Density 0.019%

    No Known Activations