© 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. 92127
    Prev
    Next
    INDEX
    Explanations

    intense emotional states and expressions of severity or concern

    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
    aste
    -0.06
    hart
    -0.06
    ilar
    -0.06
    -ID
    -0.06
     Tradable
    -0.06
    cej
    -0.06
    chodu
    -0.06
    itution
    -0.06
    .–
    -0.05
    itmap
    -0.05
    POSITIVE LOGITS
    Äħż
    0.07
    ãĥĵãĥ¼
    0.07
    оби
    0.07
     пÑĢоз
    0.07
    @dynamic
    0.07
    EventManager
    0.07
    oui
    0.07
    881
    0.06
    chalk
    0.06
    IMS
    0.06
    Activations Density 0.028%

    No Known Activations